Resubmit "[pdb] Allow zero-copy read support for symbol streams.""

Due to differences in template instantiation rules, it is not
portable to static_assert(false) inside of an invalid specialization
of a template.  Instead I just =delete the method so that it can't
be used, and leave a comment that it must be explicitly specialized.

llvm-svn: 271027
This commit is contained in:
Zachary Turner 2016-05-27 18:47:20 +00:00
parent 6c247c8cc8
commit 1de49c9ffd
16 changed files with 120 additions and 61 deletions

View File

@ -46,7 +46,7 @@ public:
#define SYMBOL_RECORD_ALIAS(EnumName, EnumVal, Name, AliasName)
#include "CVSymbolTypes.def"
void visitSymbolRecord(const SymbolIterator::Record &Record) {
void visitSymbolRecord(const CVRecord<SymbolKind> &Record) {
ArrayRef<uint8_t> Data = Record.Data;
auto *DerivedThis = static_cast<Derived *>(this);
DerivedThis->visitSymbolBegin(Record.Type, Data);

View File

@ -51,7 +51,7 @@ public:
#define MEMBER_RECORD_ALIAS(EnumName, EnumVal, Name, AliasName)
#include "TypeRecords.def"
void visitTypeRecord(const TypeIterator::Record &Record) {
void visitTypeRecord(const CVRecord<TypeLeafKind> &Record) {
ArrayRef<uint8_t> LeafData = Record.Data;
ArrayRef<uint8_t> RecordData = LeafData;
auto *DerivedThis = static_cast<Derived *>(this);

View File

@ -13,19 +13,41 @@
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/iterator_range.h"
#include "llvm/DebugInfo/CodeView/RecordSerialization.h"
#include "llvm/DebugInfo/CodeView/StreamInterface.h"
#include "llvm/DebugInfo/CodeView/StreamReader.h"
#include "llvm/Support/Endian.h"
namespace llvm {
namespace codeview {
template <typename Kind> struct CVRecord {
uint32_t Length;
Kind Type;
ArrayRef<uint8_t> Data;
};
template <typename Kind> struct VarStreamArrayExtractor<CVRecord<Kind>> {
uint32_t operator()(const StreamInterface &Stream,
CVRecord<Kind> &Item) const {
const RecordPrefix *Prefix = nullptr;
StreamReader Reader(Stream);
if (auto EC = Reader.readObject(Prefix)) {
consumeError(std::move(EC));
return 0;
}
Item.Length = Prefix->RecordLen;
Item.Type = static_cast<Kind>(uint16_t(Prefix->RecordKind));
if (auto EC = Reader.readBytes(Item.Length - 2, Item.Data)) {
consumeError(std::move(EC));
return 0;
}
return Prefix->RecordLen + 2;
}
};
// A const input iterator interface to the CodeView record stream.
template <typename Kind> class RecordIterator {
public:
struct Record {
std::size_t Length;
Kind Type;
ArrayRef<uint8_t> Data;
};
explicit RecordIterator(const ArrayRef<uint8_t> &RecordBytes, bool *HadError)
: HadError(HadError), Data(RecordBytes), AtEnd(false) {
@ -46,12 +68,12 @@ public:
return !(lhs == rhs);
}
const Record &operator*() const {
const CVRecord<Kind> &operator*() const {
assert(!AtEnd);
return Current;
}
const Record *operator->() const {
const CVRecord<Kind> *operator->() const {
assert(!AtEnd);
return &Current;
}
@ -106,7 +128,7 @@ private:
bool *HadError;
ArrayRef<uint8_t> Data;
Record Current;
CVRecord<Kind> Current;
bool AtEnd;
};

View File

@ -18,6 +18,17 @@
namespace llvm {
namespace codeview {
/// VarStreamArrayExtractor is intended to be specialized to provide customized
/// extraction logic. It should return the total number of bytes of the next
/// record (so that the array knows how much data to skip to get to the next
/// record, and it should initialize the second parameter with the desired
/// value type.
template <typename T> struct VarStreamArrayExtractor {
// Method intentionally deleted. You must provide an explicit specialization
// with the following method implemented.
uint32_t operator()(const StreamInterface &Stream, T &t) const = delete;
};
/// VarStreamArray represents an array of variable length records backed by a
/// stream. This could be a contiguous sequence of bytes in memory, it could
/// be a file on disk, or it could be a PDB stream where bytes are stored as
@ -27,33 +38,39 @@ namespace codeview {
/// re-ordering of stream data to be contiguous before iterating over it. By
/// abstracting this out, we need not duplicate this memory, and we can
/// iterate over arrays in arbitrarily formatted streams.
class VarStreamArrayIterator;
template <typename ValueType, typename Extractor> class VarStreamArrayIterator;
template <typename ValueType,
typename Extractor = VarStreamArrayExtractor<ValueType>>
class VarStreamArray {
friend class VarStreamArrayIterator;
typedef std::function<uint32_t(const StreamInterface &)> LengthFuncType;
friend class VarStreamArrayIterator<ValueType, Extractor>;
public:
template <typename LengthFunc>
VarStreamArray(StreamRef Stream, const LengthFunc &Len)
: Stream(Stream), Len(Len) {}
typedef VarStreamArrayIterator<ValueType, Extractor> Iterator;
VarStreamArrayIterator begin() const;
VarStreamArrayIterator end() const;
VarStreamArray() {}
VarStreamArray(StreamRef Stream) : Stream(Stream) {}
Iterator begin() const { return Iterator(*this); }
Iterator end() const { return Iterator(); }
private:
StreamRef Stream;
LengthFuncType Len; // Function used to calculate legth of a record
};
class VarStreamArrayIterator {
template <typename ValueType, typename Extractor> class VarStreamArrayIterator {
typedef VarStreamArrayIterator<ValueType, Extractor> IterType;
typedef VarStreamArray<ValueType, Extractor> ArrayType;
public:
VarStreamArrayIterator(const VarStreamArray &Array)
VarStreamArrayIterator(const ArrayType &Array)
: Array(&Array), IterRef(Array.Stream) {
ThisLen = Array.Len(IterRef);
ThisLen = Extract(IterRef, ThisValue);
}
VarStreamArrayIterator() : Array(nullptr), IterRef() {}
bool operator==(const VarStreamArrayIterator &R) const {
bool operator==(const IterType &R) const {
if (Array && R.Array) {
// Both have a valid array, make sure they're same.
assert(Array == R.Array);
@ -68,45 +85,37 @@ public:
return false;
}
bool operator!=(const VarStreamArrayIterator &R) { return !(*this == R); }
bool operator!=(const IterType &R) { return !(*this == R); }
StreamRef operator*() const {
ArrayRef<uint8_t> Result;
return IterRef.keep_front(ThisLen);
}
const ValueType &operator*() const { return ThisValue; }
VarStreamArrayIterator &operator++() {
if (!Array || IterRef.getLength() == 0)
IterType &operator++() {
if (!Array || IterRef.getLength() == 0 || ThisLen == 0)
return *this;
IterRef = IterRef.drop_front(ThisLen);
if (IterRef.getLength() == 0) {
Array = nullptr;
ThisLen = 0;
} else {
ThisLen = Array->Len(IterRef);
ThisLen = Extract(IterRef, ThisValue);
}
return *this;
}
VarStreamArrayIterator operator++(int) {
VarStreamArrayIterator Original = *this;
IterType operator++(int) {
IterType Original = *this;
++*this;
return Original;
}
private:
const VarStreamArray *Array;
const ArrayType *Array;
uint32_t ThisLen;
ValueType ThisValue;
StreamRef IterRef;
Extractor Extract;
};
inline VarStreamArrayIterator VarStreamArray::begin() const {
return VarStreamArrayIterator(*this);
}
inline VarStreamArrayIterator VarStreamArray::end() const {
return VarStreamArrayIterator();
}
template <typename T> class FixedStreamArrayIterator;
template <typename T> class FixedStreamArray {

View File

@ -45,6 +45,15 @@ public:
return Error::success();
}
template <typename T>
Error readArray(VarStreamArray<T> &Array, uint32_t Size) {
StreamRef S;
if (auto EC = readStreamRef(S, Size))
return EC;
Array = VarStreamArray<T>(S);
return Error::success();
}
template <typename T>
Error readArray(FixedStreamArray<T> &Array, uint32_t NumItems) {
if (NumItems == 0) {

View File

@ -35,7 +35,7 @@ public:
/// and true otherwise. This should be called in order, since the dumper
/// maintains state about previous records which are necessary for cross
/// type references.
bool dump(const SymbolIterator::Record &Record);
bool dump(const CVRecord<SymbolKind> &Record);
/// Dumps the type records in Data. Returns false if there was a type stream
/// parse error, and true otherwise.

View File

@ -15,6 +15,8 @@
#include "llvm/DebugInfo/CodeView/CodeView.h"
#include "llvm/DebugInfo/CodeView/RecordIterator.h"
#include "llvm/DebugInfo/CodeView/RecordSerialization.h"
#include "llvm/DebugInfo/CodeView/StreamArray.h"
#include "llvm/DebugInfo/CodeView/StreamInterface.h"
#include "llvm/DebugInfo/CodeView/TypeIndex.h"
#include "llvm/Support/Endian.h"
#include "llvm/Support/Error.h"
@ -1441,6 +1443,8 @@ public:
};
typedef RecordIterator<SymbolKind> SymbolIterator;
typedef CVRecord<SymbolKind> CVSymbol;
typedef VarStreamArray<CVSymbol> CVSymbolArray;
inline iterator_range<SymbolIterator> makeSymbolRange(ArrayRef<uint8_t> Data,
bool *HadError) {

View File

@ -34,7 +34,7 @@ public:
/// and true otherwise. This should be called in order, since the dumper
/// maintains state about previous records which are necessary for cross
/// type references.
bool dump(const TypeIterator::Record &Record);
bool dump(const CVRecord<TypeLeafKind> &Record);
/// Dumps the type records in Data. Returns false if there was a type stream
/// parse error, and true otherwise.

View File

@ -10,7 +10,6 @@
#ifndef LLVM_DEBUGINFO_PDB_RAW_PDBDBISTREAM_H
#define LLVM_DEBUGINFO_PDB_RAW_PDBDBISTREAM_H
#include "llvm/DebugInfo/CodeView/ByteStream.h"
#include "llvm/DebugInfo/CodeView/StreamArray.h"
#include "llvm/DebugInfo/CodeView/StreamRef.h"
#include "llvm/DebugInfo/PDB/PDBTypes.h"

View File

@ -11,6 +11,7 @@
#define LLVM_DEBUGINFO_PDB_RAW_MODINFO_H
#include "llvm/ADT/StringRef.h"
#include "llvm/DebugInfo/CodeView/StreamArray.h"
#include "llvm/DebugInfo/CodeView/StreamRef.h"
#include <cstdint>
#include <vector>
@ -23,6 +24,7 @@ private:
struct FileLayout;
public:
ModInfo();
ModInfo(codeview::StreamRef Stream);
ModInfo(const ModInfo &Info);
~ModInfo();
@ -50,6 +52,7 @@ private:
struct ModuleInfoEx {
ModuleInfoEx(codeview::StreamRef Stream) : Info(Stream) {}
ModuleInfoEx(const ModInfo &Info) : Info(Info) {}
ModuleInfoEx(const ModuleInfoEx &Ex)
: Info(Ex.Info), SourceFiles(Ex.SourceFiles) {}
@ -57,11 +60,17 @@ struct ModuleInfoEx {
std::vector<StringRef> SourceFiles;
};
inline uint32_t ModInfoRecordLength(const codeview::StreamInterface &Stream) {
return ModInfo(Stream).getRecordLength();
} // end namespace pdb
namespace codeview {
template <> struct VarStreamArrayExtractor<pdb::ModInfo> {
uint32_t operator()(const StreamInterface &Stream, pdb::ModInfo &Info) const {
Info = pdb::ModInfo(Stream);
return Info.getRecordLength();
}
};
}
} // end namespace pdb
} // end namespace llvm
#endif // LLVM_DEBUGINFO_PDB_RAW_MODINFO_H

View File

@ -11,7 +11,7 @@
#define LLVM_DEBUGINFO_PDB_RAW_MODSTREAM_H
#include "llvm/ADT/iterator_range.h"
#include "llvm/DebugInfo/CodeView/ByteStream.h"
#include "llvm/DebugInfo/CodeView/RecordIterator.h"
#include "llvm/DebugInfo/CodeView/StreamRef.h"
#include "llvm/DebugInfo/CodeView/SymbolRecord.h"
#include "llvm/DebugInfo/PDB/Raw/MappedBlockStream.h"
@ -29,14 +29,14 @@ public:
Error reload();
iterator_range<codeview::SymbolIterator> symbols() const;
iterator_range<codeview::CVSymbolArray::Iterator> symbols() const;
private:
const ModInfo &Mod;
MappedBlockStream Stream;
codeview::ByteStream SymbolsSubstream;
codeview::CVSymbolArray SymbolsSubstream;
codeview::StreamRef LinesSubstream;
codeview::StreamRef C13LinesSubstream;
codeview::StreamRef GlobalRefsSubstream;

View File

@ -866,7 +866,7 @@ void CVSymbolDumperImpl::visitUnknownSymbol(SymbolKind Kind,
W.printNumber("Length", uint32_t(Data.size()));
}
bool CVSymbolDumper::dump(const SymbolIterator::Record &Record) {
bool CVSymbolDumper::dump(const CVRecord<SymbolKind> &Record) {
CVSymbolDumperImpl Dumper(CVTD, ObjDelegate.get(), W, PrintRecordBytes);
Dumper.visitSymbolRecord(Record);
return !Dumper.hadError();

View File

@ -676,7 +676,7 @@ void CVTypeDumper::printTypeIndex(StringRef FieldName, TypeIndex TI) {
W->printHex(FieldName, TI.getIndex());
}
bool CVTypeDumper::dump(const TypeIterator::Record &Record) {
bool CVTypeDumper::dump(const CVRecord<TypeLeafKind> &Record) {
assert(W && "printer should not be null");
CVTypeDumperImpl Dumper(*this, *W, PrintRecordBytes);
Dumper.visitTypeRecord(Record);

View File

@ -136,14 +136,12 @@ Error DbiStream::reload() {
return make_error<RawError>(raw_error_code::corrupt_file,
"DBI type server substream not aligned.");
if (auto EC =
Reader.readStreamRef(ModInfoSubstream, Header->ModiSubstreamSize))
return EC;
// Since each ModInfo in the stream is a variable length, we have to iterate
// them to know how many there actually are.
codeview::VarStreamArray ModInfoArray(ModInfoSubstream, ModInfoRecordLength);
for (auto Info : ModInfoArray) {
codeview::VarStreamArray<ModInfo> ModInfoArray;
if (auto EC = Reader.readArray(ModInfoArray, Header->ModiSubstreamSize))
return EC;
for (auto &Info : ModInfoArray) {
ModuleInfos.emplace_back(Info);
}

View File

@ -67,6 +67,8 @@ struct ModInfo::FileLayout {
// Null terminated Obj File Name
};
ModInfo::ModInfo() : Layout(nullptr) {}
ModInfo::ModInfo(codeview::StreamRef Stream) : Layout(nullptr) {
codeview::StreamReader Reader(Stream);
if (auto EC = Reader.readObject(Layout)) {

View File

@ -9,6 +9,7 @@
#include "llvm/DebugInfo/PDB/Raw/ModStream.h"
#include "llvm/DebugInfo/CodeView/RecordIterator.h"
#include "llvm/DebugInfo/CodeView/StreamReader.h"
#include "llvm/DebugInfo/PDB/Raw/ModInfo.h"
#include "llvm/DebugInfo/PDB/Raw/RawError.h"
@ -32,8 +33,14 @@ Error ModStream::reload() {
return llvm::make_error<RawError>(raw_error_code::corrupt_file,
"Module has both C11 and C13 line info");
if (auto EC = SymbolsSubstream.load(Reader, SymbolSize))
codeview::StreamRef S;
uint32_t SymbolSubstreamSig = 0;
if (auto EC = Reader.readInteger(SymbolSubstreamSig))
return EC;
if (auto EC = Reader.readArray(SymbolsSubstream, SymbolSize - 4))
return EC;
if (auto EC = Reader.readStreamRef(LinesSubstream, C11Size))
return EC;
if (auto EC = Reader.readStreamRef(C13LinesSubstream, C13Size))
@ -51,6 +58,6 @@ Error ModStream::reload() {
return Error::success();
}
iterator_range<codeview::SymbolIterator> ModStream::symbols() const {
return codeview::makeSymbolRange(SymbolsSubstream.data().slice(4), nullptr);
iterator_range<codeview::CVSymbolArray::Iterator> ModStream::symbols() const {
return llvm::make_range(SymbolsSubstream.begin(), SymbolsSubstream.end());
}