[pdb] added support for dumping globals stream
Summary: This adds support for dumping the globals stream from PDB files using llvm-pdbdump, similar to the support we have for the publics stream.
Reviewers: ruiu, zturner
Subscribers: beanz, mgorny, modocache
Differential Revision: https://reviews.llvm.org/D25801
llvm-svn: 284861
diff --git a/llvm/lib/DebugInfo/PDB/CMakeLists.txt b/llvm/lib/DebugInfo/PDB/CMakeLists.txt
index f28cbe7..04144f2 100644
--- a/llvm/lib/DebugInfo/PDB/CMakeLists.txt
+++ b/llvm/lib/DebugInfo/PDB/CMakeLists.txt
@@ -31,6 +31,8 @@
Raw/DbiStream.cpp
Raw/DbiStreamBuilder.cpp
Raw/EnumTables.cpp
+ Raw/GlobalsStream.cpp
+ Raw/GSI.cpp
Raw/Hash.cpp
Raw/InfoStream.cpp
Raw/InfoStreamBuilder.cpp
diff --git a/llvm/lib/DebugInfo/PDB/Raw/GSI.cpp b/llvm/lib/DebugInfo/PDB/Raw/GSI.cpp
new file mode 100644
index 0000000..6ecbb5c
--- /dev/null
+++ b/llvm/lib/DebugInfo/PDB/Raw/GSI.cpp
@@ -0,0 +1,93 @@
+//===- GSI.cpp - Common Functions for GlobalsStream and PublicsStream ----===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "GSI.h"
+
+#include "llvm/DebugInfo/MSF/StreamArray.h"
+#include "llvm/DebugInfo/MSF/StreamReader.h"
+#include "llvm/DebugInfo/PDB/Raw/RawError.h"
+#include "llvm/DebugInfo/PDB/Raw/RawTypes.h"
+
+#include "llvm/Support/Error.h"
+
+namespace llvm {
+namespace pdb {
+
+static Error checkHashHdrVersion(const GSIHashHeader *HashHdr) {
+ if (HashHdr->VerHdr != GSIHashHeader::HdrVersion)
+ return make_error<RawError>(
+ raw_error_code::feature_unsupported,
+ "Encountered unsupported globals stream version.");
+
+ return Error::success();
+}
+
+Error readGSIHashBuckets(
+ msf::FixedStreamArray<support::ulittle32_t> &HashBuckets,
+ const GSIHashHeader *HashHdr, msf::StreamReader &Reader) {
+ if (auto EC = checkHashHdrVersion(HashHdr))
+ return EC;
+
+ // Before the actual hash buckets, there is a bitmap of length determined by
+ // IPHR_HASH.
+ ArrayRef<uint8_t> Bitmap;
+ size_t BitmapSizeInBits = alignTo(IPHR_HASH + 1, 32);
+ uint32_t NumBitmapEntries = BitmapSizeInBits / 8;
+ if (auto EC = Reader.readBytes(Bitmap, NumBitmapEntries))
+ return joinErrors(std::move(EC),
+ make_error<RawError>(raw_error_code::corrupt_file,
+ "Could not read a bitmap."));
+ uint32_t NumBuckets = 0;
+ for (uint8_t B : Bitmap)
+ NumBuckets += countPopulation(B);
+
+ // Hash buckets follow.
+ if (auto EC = Reader.readArray(HashBuckets, NumBuckets))
+ return joinErrors(std::move(EC),
+ make_error<RawError>(raw_error_code::corrupt_file,
+ "Hash buckets corrupted."));
+
+ return Error::success();
+}
+
+Error readGSIHashHeader(const GSIHashHeader *&HashHdr,
+ msf::StreamReader &Reader) {
+ if (Reader.readObject(HashHdr))
+ return make_error<RawError>(raw_error_code::corrupt_file,
+ "Stream does not contain a GSIHashHeader.");
+
+ if (HashHdr->VerSignature != GSIHashHeader::HdrSignature)
+ return make_error<RawError>(
+ raw_error_code::feature_unsupported,
+ "GSIHashHeader signature (0xffffffff) not found.");
+
+ return Error::success();
+}
+
+Error readGSIHashRecords(msf::FixedStreamArray<PSHashRecord> &HashRecords,
+ const GSIHashHeader *HashHdr,
+ msf::StreamReader &Reader) {
+ if (auto EC = checkHashHdrVersion(HashHdr))
+ return EC;
+
+ // HashHdr->HrSize specifies the number of bytes of PSHashRecords we have.
+ // Verify that we can read them all.
+ if (HashHdr->HrSize % sizeof(PSHashRecord))
+ return make_error<RawError>(raw_error_code::corrupt_file,
+ "Invalid HR array size.");
+ uint32_t NumHashRecords = HashHdr->HrSize / sizeof(PSHashRecord);
+ if (auto EC = Reader.readArray(HashRecords, NumHashRecords))
+ return joinErrors(std::move(EC),
+ make_error<RawError>(raw_error_code::corrupt_file,
+ "Error reading hash records."));
+
+ return Error::success();
+}
+}
+}
diff --git a/llvm/lib/DebugInfo/PDB/Raw/GSI.h b/llvm/lib/DebugInfo/PDB/Raw/GSI.h
new file mode 100644
index 0000000..82cebd9
--- /dev/null
+++ b/llvm/lib/DebugInfo/PDB/Raw/GSI.h
@@ -0,0 +1,70 @@
+//===- GSI.h - Common Declarations for GlobalsStream and PublicsStream ----===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// The data structures defined in this file are based on the reference
+// implementation which is available at
+// https://github.com/Microsoft/microsoft-pdb/blob/master/PDB/dbi/gsi.h
+//
+// When you are reading the reference source code, you'd find the
+// information below useful.
+//
+// - ppdb1->m_fMinimalDbgInfo seems to be always true.
+// - SMALLBUCKETS macro is defined.
+//
+// The reference doesn't compile, so I learned just by reading code.
+// It's not guaranteed to be correct.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIB_DEBUGINFO_PDB_RAW_GSI_H
+#define LLVM_LIB_DEBUGINFO_PDB_RAW_GSI_H
+
+#include "llvm/DebugInfo/MSF/StreamArray.h"
+#include "llvm/DebugInfo/PDB/Raw/RawTypes.h"
+
+#include "llvm/Support/Endian.h"
+#include "llvm/Support/Error.h"
+
+namespace llvm {
+
+namespace msf {
+class StreamReader;
+}
+
+namespace pdb {
+
+/// From https://github.com/Microsoft/microsoft-pdb/blob/master/PDB/dbi/gsi.cpp
+static const unsigned IPHR_HASH = 4096;
+
+/// Header of the hash tables found in the globals and publics sections.
+/// Based on GSIHashHeader in
+/// https://github.com/Microsoft/microsoft-pdb/blob/master/PDB/dbi/gsi.h
+struct GSIHashHeader {
+ enum : unsigned {
+ HdrSignature = ~0U,
+ HdrVersion = 0xeffe0000 + 19990810,
+ };
+ support::ulittle32_t VerSignature;
+ support::ulittle32_t VerHdr;
+ support::ulittle32_t HrSize;
+ support::ulittle32_t NumBuckets;
+};
+
+Error readGSIHashBuckets(
+ msf::FixedStreamArray<support::ulittle32_t> &HashBuckets,
+ const GSIHashHeader *HashHdr, msf::StreamReader &Reader);
+Error readGSIHashHeader(const GSIHashHeader *&HashHdr,
+ msf::StreamReader &Reader);
+Error readGSIHashRecords(msf::FixedStreamArray<PSHashRecord> &HashRecords,
+ const GSIHashHeader *HashHdr,
+ msf::StreamReader &Reader);
+}
+}
+
+#endif
diff --git a/llvm/lib/DebugInfo/PDB/Raw/GlobalsStream.cpp b/llvm/lib/DebugInfo/PDB/Raw/GlobalsStream.cpp
new file mode 100644
index 0000000..c518452
--- /dev/null
+++ b/llvm/lib/DebugInfo/PDB/Raw/GlobalsStream.cpp
@@ -0,0 +1,46 @@
+//===- GlobalsStream.cpp - PDB Index of Symbols by Name ---- ----*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/DebugInfo/PDB/Raw/GlobalsStream.h"
+
+#include "GSI.h"
+#include "llvm/DebugInfo/PDB/Raw/PDBFile.h"
+#include "llvm/DebugInfo/PDB/Raw/RawError.h"
+#include "llvm/DebugInfo/PDB/Raw/RawTypes.h"
+
+#include "llvm/Support/Endian.h"
+#include "llvm/Support/Error.h"
+
+using namespace llvm;
+using namespace llvm::msf;
+using namespace llvm::pdb;
+
+GlobalsStream::GlobalsStream(std::unique_ptr<MappedBlockStream> Stream)
+ : Stream(std::move(Stream)) {}
+
+GlobalsStream::~GlobalsStream() {}
+
+Error GlobalsStream::reload() {
+ StreamReader Reader(*Stream);
+
+ const GSIHashHeader *HashHdr;
+ if (auto EC = readGSIHashHeader(HashHdr, Reader))
+ return EC;
+
+ if (auto EC = readGSIHashRecords(HashRecords, HashHdr, Reader))
+ return EC;
+
+ if (auto EC = readGSIHashBuckets(HashBuckets, HashHdr, Reader))
+ return EC;
+ NumBuckets = HashBuckets.size();
+
+ return Error::success();
+}
+
+Error GlobalsStream::commit() { return Error::success(); }
diff --git a/llvm/lib/DebugInfo/PDB/Raw/PDBFile.cpp b/llvm/lib/DebugInfo/PDB/Raw/PDBFile.cpp
index 75840b0..f7bb8ab 100644
--- a/llvm/lib/DebugInfo/PDB/Raw/PDBFile.cpp
+++ b/llvm/lib/DebugInfo/PDB/Raw/PDBFile.cpp
@@ -15,6 +15,7 @@
#include "llvm/DebugInfo/MSF/StreamReader.h"
#include "llvm/DebugInfo/MSF/StreamWriter.h"
#include "llvm/DebugInfo/PDB/Raw/DbiStream.h"
+#include "llvm/DebugInfo/PDB/Raw/GlobalsStream.h"
#include "llvm/DebugInfo/PDB/Raw/InfoStream.h"
#include "llvm/DebugInfo/PDB/Raw/NameHashTable.h"
#include "llvm/DebugInfo/PDB/Raw/PublicsStream.h"
@@ -217,6 +218,22 @@
return ContainerLayout.DirectoryBlocks;
}
+Expected<GlobalsStream &> PDBFile::getPDBGlobalsStream() {
+ if (!Globals) {
+ auto DbiS = getPDBDbiStream();
+ if (!DbiS)
+ return DbiS.takeError();
+
+ auto GlobalS = MappedBlockStream::createIndexedStream(
+ ContainerLayout, *Buffer, DbiS->getGlobalSymbolStreamIndex());
+ auto TempGlobals = llvm::make_unique<GlobalsStream>(std::move(GlobalS));
+ if (auto EC = TempGlobals->reload())
+ return std::move(EC);
+ Globals = std::move(TempGlobals);
+ }
+ return *Globals;
+}
+
Expected<InfoStream &> PDBFile::getPDBInfoStream() {
if (!Info) {
auto InfoS = MappedBlockStream::createIndexedStream(ContainerLayout,
diff --git a/llvm/lib/DebugInfo/PDB/Raw/PublicsStream.cpp b/llvm/lib/DebugInfo/PDB/Raw/PublicsStream.cpp
index 5d4431d..43ac4e5 100644
--- a/llvm/lib/DebugInfo/PDB/Raw/PublicsStream.cpp
+++ b/llvm/lib/DebugInfo/PDB/Raw/PublicsStream.cpp
@@ -24,6 +24,7 @@
#include "llvm/DebugInfo/PDB/Raw/PublicsStream.h"
+#include "GSI.h"
#include "llvm/DebugInfo/CodeView/CodeView.h"
#include "llvm/DebugInfo/CodeView/TypeRecord.h"
#include "llvm/DebugInfo/MSF/MappedBlockStream.h"
@@ -44,8 +45,6 @@
using namespace llvm::pdb;
-static const unsigned IPHR_HASH = 4096;
-
// This is PSGSIHDR struct defined in
// https://github.com/Microsoft/microsoft-pdb/blob/master/PDB/dbi/gsi.h
struct PublicsStream::HeaderInfo {
@@ -59,18 +58,6 @@
ulittle32_t NumSections;
};
-// This is GSIHashHdr.
-struct PublicsStream::GSIHashHeader {
- enum : unsigned {
- HdrSignature = ~0U,
- HdrVersion = 0xeffe0000 + 19990810,
- };
- ulittle32_t VerSignature;
- ulittle32_t VerHdr;
- ulittle32_t HrSize;
- ulittle32_t NumBuckets;
-};
-
PublicsStream::PublicsStream(PDBFile &File,
std::unique_ptr<MappedBlockStream> Stream)
: Pdb(File), Stream(std::move(Stream)) {}
@@ -98,40 +85,15 @@
return make_error<RawError>(raw_error_code::corrupt_file,
"Publics Stream does not contain a header.");
- if (Reader.readObject(HashHdr))
- return make_error<RawError>(raw_error_code::corrupt_file,
- "Publics Stream does not contain a header.");
+ if (auto EC = readGSIHashHeader(HashHdr, Reader))
+ return EC;
- // An array of HashRecord follows. Read them.
- if (HashHdr->HrSize % sizeof(PSHashRecord))
- return make_error<RawError>(raw_error_code::corrupt_file,
- "Invalid HR array size.");
- uint32_t NumHashRecords = HashHdr->HrSize / sizeof(PSHashRecord);
- if (auto EC = Reader.readArray(HashRecords, NumHashRecords))
- return joinErrors(std::move(EC),
- make_error<RawError>(raw_error_code::corrupt_file,
- "Could not read an HR array"));
+ if (auto EC = readGSIHashRecords(HashRecords, HashHdr, Reader))
+ return EC;
- // A bitmap of a fixed length follows.
- size_t BitmapSizeInBits = alignTo(IPHR_HASH + 1, 32);
- uint32_t NumBitmapEntries = BitmapSizeInBits / 8;
- if (auto EC = Reader.readBytes(Bitmap, NumBitmapEntries))
- return joinErrors(std::move(EC),
- make_error<RawError>(raw_error_code::corrupt_file,
- "Could not read a bitmap."));
- for (uint8_t B : Bitmap)
- NumBuckets += countPopulation(B);
-
- // We don't yet understand the following data structures completely,
- // but we at least know the types and sizes. Here we are trying
- // to read the stream till end so that we at least can detect
- // corrupted streams.
-
- // Hash buckets follow.
- if (auto EC = Reader.readArray(HashBuckets, NumBuckets))
- return joinErrors(std::move(EC),
- make_error<RawError>(raw_error_code::corrupt_file,
- "Hash buckets corrupted."));
+ if (auto EC = readGSIHashBuckets(HashBuckets, HashHdr, Reader))
+ return EC;
+ NumBuckets = HashBuckets.size();
// Something called "address map" follows.
uint32_t NumAddressMapEntries = Header->AddrMap / sizeof(uint32_t);