Bitcode: Change reader interface to take memory buffers.
As proposed on llvm-dev:
http://lists.llvm.org/pipermail/llvm-dev/2016-October/106595.html
This change also fixes an API oddity where BitstreamCursor::Read() would
return zero for the first read past the end of the bitstream, but would
report_fatal_error for subsequent reads. Now we always report_fatal_error
for all reads past the end. Updated clients to check for the end of the
bitstream before reading from it.
I also needed to add padding to the invalid bitcode tests in
test/Bitcode/. This is because the streaming interface was not checking that
the file size is a multiple of 4.
Differential Revision: https://reviews.llvm.org/D26219
llvm-svn: 285773
diff --git a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
index f224b04..710187a 100644
--- a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
+++ b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -61,14 +61,12 @@
#include "llvm/Support/Casting.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Compiler.h"
-#include "llvm/Support/DataStream.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/ErrorOr.h"
#include "llvm/Support/ManagedStatic.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/raw_ostream.h"
-#include "llvm/Support/StreamingMemoryObject.h"
#include <algorithm>
#include <cassert>
#include <cstddef>
@@ -232,29 +230,19 @@
class BitcodeReaderBase {
protected:
- BitcodeReaderBase() = default;
BitcodeReaderBase(MemoryBuffer *Buffer) : Buffer(Buffer) {}
std::unique_ptr<MemoryBuffer> Buffer;
std::unique_ptr<BitstreamReader> StreamFile;
BitstreamCursor Stream;
- std::error_code initStream(std::unique_ptr<DataStreamer> Streamer);
- std::error_code initStreamFromBuffer();
- std::error_code initLazyStream(std::unique_ptr<DataStreamer> Streamer);
+ std::error_code initStream();
virtual std::error_code error(const Twine &Message) = 0;
virtual ~BitcodeReaderBase() = default;
};
-std::error_code
-BitcodeReaderBase::initStream(std::unique_ptr<DataStreamer> Streamer) {
- if (Streamer)
- return initLazyStream(std::move(Streamer));
- return initStreamFromBuffer();
-}
-
-std::error_code BitcodeReaderBase::initStreamFromBuffer() {
+std::error_code BitcodeReaderBase::initStream() {
const unsigned char *BufPtr = (const unsigned char*)Buffer->getBufferStart();
const unsigned char *BufEnd = BufPtr+Buffer->getBufferSize();
@@ -267,39 +255,12 @@
if (SkipBitcodeWrapperHeader(BufPtr, BufEnd, true))
return error("Invalid bitcode wrapper header");
- StreamFile.reset(new BitstreamReader(BufPtr, BufEnd));
+ StreamFile.reset(new BitstreamReader(ArrayRef<uint8_t>(BufPtr, BufEnd)));
Stream.init(&*StreamFile);
return std::error_code();
}
-std::error_code
-BitcodeReaderBase::initLazyStream(std::unique_ptr<DataStreamer> Streamer) {
- // Check and strip off the bitcode wrapper; BitstreamReader expects never to
- // see it.
- auto OwnedBytes =
- llvm::make_unique<StreamingMemoryObject>(std::move(Streamer));
- StreamingMemoryObject &Bytes = *OwnedBytes;
- StreamFile = llvm::make_unique<BitstreamReader>(std::move(OwnedBytes));
- Stream.init(&*StreamFile);
-
- unsigned char buf[16];
- if (Bytes.readBytes(buf, 16, 0) != 16)
- return error("Invalid bitcode signature");
-
- if (!isBitcode(buf, buf + 16))
- return error("Invalid bitcode signature");
-
- if (isBitcodeWrapper(buf, buf + 4)) {
- const unsigned char *bitcodeStart = buf;
- const unsigned char *bitcodeEnd = buf + 16;
- SkipBitcodeWrapperHeader(bitcodeStart, bitcodeEnd, false);
- Bytes.dropLeadingBytes(bitcodeStart - buf);
- Bytes.setKnownObjectSize(bitcodeEnd - bitcodeStart);
- }
- return std::error_code();
-}
-
class BitcodeReader : public BitcodeReaderBase, public GVMaterializer {
LLVMContext &Context;
Module *TheModule = nullptr;
@@ -399,7 +360,6 @@
std::error_code error(const Twine &Message) override;
BitcodeReader(MemoryBuffer *Buffer, LLVMContext &Context);
- BitcodeReader(LLVMContext &Context);
~BitcodeReader() override { freeState(); }
std::error_code materializeForwardReferencedFunctions();
@@ -414,8 +374,7 @@
/// \brief Main interface to parsing a bitcode buffer.
/// \returns true if an error occurred.
- std::error_code parseBitcodeInto(std::unique_ptr<DataStreamer> Streamer,
- Module *M,
+ std::error_code parseBitcodeInto(Module *M,
bool ShouldLazyLoadMetadata = false);
/// \brief Cheap mechanism to just extract module triple
@@ -638,8 +597,7 @@
/// \brief Main interface to parsing a bitcode buffer.
/// \returns true if an error occurred.
- std::error_code parseSummaryIndexInto(std::unique_ptr<DataStreamer> Streamer,
- ModuleSummaryIndex *I);
+ std::error_code parseSummaryIndexInto(ModuleSummaryIndex *I);
private:
std::error_code parseModule();
@@ -706,9 +664,6 @@
: BitcodeReaderBase(Buffer), Context(Context), ValueList(Context),
MetadataList(Context) {}
-BitcodeReader::BitcodeReader(LLVMContext &Context)
- : Context(Context), ValueList(Context), MetadataList(Context) {}
-
std::error_code BitcodeReader::materializeForwardReferencedFunctions() {
if (WillMaterializeAllForwardRefs)
return std::error_code();
@@ -2166,10 +2121,6 @@
SimpleBitstreamCursor R(*StreamFile);
R.jumpToPointer(Lengths.begin());
- // Ensure that Blob doesn't get invalidated, even if this is reading from
- // a StreamingMemoryObject with corrupt data.
- R.setArtificialByteLimit(R.getCurrentByteNo() + StringsOffset);
-
StringRef Strings = Blob.drop_front(StringsOffset);
do {
if (R.AtEndOfStream())
@@ -4203,12 +4154,11 @@
return true;
}
-std::error_code
-BitcodeReader::parseBitcodeInto(std::unique_ptr<DataStreamer> Streamer,
- Module *M, bool ShouldLazyLoadMetadata) {
+std::error_code BitcodeReader::parseBitcodeInto(Module *M,
+ bool ShouldLazyLoadMetadata) {
TheModule = M;
- if (std::error_code EC = initStream(std::move(Streamer)))
+ if (std::error_code EC = initStream())
return EC;
// Sniff for the signature.
@@ -4282,7 +4232,7 @@
}
ErrorOr<std::string> BitcodeReader::parseTriple() {
- if (std::error_code EC = initStream(nullptr))
+ if (std::error_code EC = initStream())
return EC;
// Sniff for the signature.
@@ -4317,7 +4267,7 @@
}
ErrorOr<std::string> BitcodeReader::parseIdentificationBlock() {
- if (std::error_code EC = initStream(nullptr))
+ if (std::error_code EC = initStream())
return EC;
// Sniff for the signature.
@@ -4367,7 +4317,7 @@
}
ErrorOr<bool> BitcodeReader::hasObjCCategory() {
- if (std::error_code EC = initStream(nullptr))
+ if (std::error_code EC = initStream())
return EC;
// Sniff for the signature.
@@ -5955,7 +5905,8 @@
ModuleSummaryIndexBitcodeReader::ModuleSummaryIndexBitcodeReader(
MemoryBuffer *Buffer, DiagnosticHandlerFunction DiagnosticHandler,
bool CheckGlobalValSummaryPresenceOnly)
- : BitcodeReaderBase(Buffer), DiagnosticHandler(std::move(DiagnosticHandler)),
+ : BitcodeReaderBase(Buffer),
+ DiagnosticHandler(std::move(DiagnosticHandler)),
CheckGlobalValSummaryPresenceOnly(CheckGlobalValSummaryPresenceOnly) {}
void ModuleSummaryIndexBitcodeReader::freeState() { Buffer = nullptr; }
@@ -6555,11 +6506,11 @@
}
// Parse the function info index from the bitcode streamer into the given index.
-std::error_code ModuleSummaryIndexBitcodeReader::parseSummaryIndexInto(
- std::unique_ptr<DataStreamer> Streamer, ModuleSummaryIndex *I) {
+std::error_code
+ModuleSummaryIndexBitcodeReader::parseSummaryIndexInto(ModuleSummaryIndex *I) {
TheIndex = I;
- if (std::error_code EC = initStream(std::move(Streamer)))
+ if (std::error_code EC = initStream())
return EC;
// Sniff for the signature.
@@ -6624,8 +6575,7 @@
//===----------------------------------------------------------------------===//
static ErrorOr<std::unique_ptr<Module>>
-getBitcodeModuleImpl(std::unique_ptr<DataStreamer> Streamer, StringRef Name,
- BitcodeReader *R, LLVMContext &Context,
+getBitcodeModuleImpl(StringRef Name, BitcodeReader *R, LLVMContext &Context,
bool MaterializeAll, bool ShouldLazyLoadMetadata) {
std::unique_ptr<Module> M = llvm::make_unique<Module>(Name, Context);
M->setMaterializer(R);
@@ -6636,8 +6586,7 @@
};
// Delay parsing Metadata if ShouldLazyLoadMetadata is true.
- if (std::error_code EC = R->parseBitcodeInto(std::move(Streamer), M.get(),
- ShouldLazyLoadMetadata))
+ if (std::error_code EC = R->parseBitcodeInto(M.get(), ShouldLazyLoadMetadata))
return cleanupOnError(EC);
if (MaterializeAll) {
@@ -6667,7 +6616,7 @@
BitcodeReader *R = new BitcodeReader(Buffer.get(), Context);
ErrorOr<std::unique_ptr<Module>> Ret =
- getBitcodeModuleImpl(nullptr, Buffer->getBufferIdentifier(), R, Context,
+ getBitcodeModuleImpl(Buffer->getBufferIdentifier(), R, Context,
MaterializeAll, ShouldLazyLoadMetadata);
if (!Ret)
return Ret;
@@ -6683,17 +6632,6 @@
ShouldLazyLoadMetadata);
}
-ErrorOr<std::unique_ptr<Module>>
-llvm::getStreamedBitcodeModule(StringRef Name,
- std::unique_ptr<DataStreamer> Streamer,
- LLVMContext &Context) {
- std::unique_ptr<Module> M = llvm::make_unique<Module>(Name, Context);
- BitcodeReader *R = new BitcodeReader(Context);
-
- return getBitcodeModuleImpl(std::move(Streamer), Name, R, Context, false,
- false);
-}
-
ErrorOr<std::unique_ptr<Module>> llvm::parseBitcodeFile(MemoryBufferRef Buffer,
LLVMContext &Context) {
std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false);
@@ -6746,7 +6684,7 @@
return EC;
};
- if (std::error_code EC = R.parseSummaryIndexInto(nullptr, Index.get()))
+ if (std::error_code EC = R.parseSummaryIndexInto(Index.get()))
return cleanupOnError(EC);
Buf.release(); // The ModuleSummaryIndexBitcodeReader owns it now.
@@ -6765,7 +6703,7 @@
return false;
};
- if (std::error_code EC = R.parseSummaryIndexInto(nullptr, nullptr))
+ if (std::error_code EC = R.parseSummaryIndexInto(nullptr))
return cleanupOnError(EC);
Buf.release(); // The ModuleSummaryIndexBitcodeReader owns it now.