pdbdump: print out symbol names referred by publics stream.

DBI stream contains a stream number of the symbol record stream.
Symbol record streams is an array of length-type-value members.
Each member represents one symbol.

Publics stream contains offsets to the symbol record stream.
This patch is to print out all symbols that are referenced by
the publics stream.

Note that even with this patch, llvm-pdbdump cannot dump all the
information in a publics stream since it contains more information
than symbol names. I'll improve it in followup patches.

Differential Revision: http://reviews.llvm.org/D20480

llvm-svn: 270262

4 files changed, 129 insertions, 9 deletions

diff --git a/llvm/lib/DebugInfo/PDB/CMakeLists.txt b/llvm/lib/DebugInfo/PDB/CMakeLists.txt
index bda67468df5..b5053c51f3a 100644
--- a/llvm/lib/DebugInfo/PDB/CMakeLists.txt
+++ b/llvm/lib/DebugInfo/PDB/CMakeLists.txt
@@ -41,6 +41,7 @@ add_pdb_impl_folder(Raw
   Raw/RawError.cpp
   Raw/RawSession.cpp
   Raw/StreamReader.cpp
+  Raw/SymbolStream.cpp
   Raw/TpiStream.cpp)
 
 list(APPEND LIBPDB_ADDITIONAL_HEADER_DIRS "${LLVM_MAIN_INCLUDE_DIR}/llvm/DebugInfo/PDB")
diff --git a/llvm/lib/DebugInfo/PDB/Raw/PDBFile.cpp b/llvm/lib/DebugInfo/PDB/Raw/PDBFile.cpp
index d587704c62c..a8143a946e2 100644
--- a/llvm/lib/DebugInfo/PDB/Raw/PDBFile.cpp
+++ b/llvm/lib/DebugInfo/PDB/Raw/PDBFile.cpp
@@ -13,6 +13,7 @@
 #include "llvm/DebugInfo/PDB/Raw/InfoStream.h"
 #include "llvm/DebugInfo/PDB/Raw/PublicsStream.h"
 #include "llvm/DebugInfo/PDB/Raw/RawError.h"
+#include "llvm/DebugInfo/PDB/Raw/SymbolStream.h"
 #include "llvm/DebugInfo/PDB/Raw/TpiStream.h"
 #include "llvm/Support/Endian.h"
 #include "llvm/Support/MemoryBuffer.h"
@@ -307,3 +308,17 @@ Expected<PublicsStream &> PDBFile::getPDBPublicsStream() {
   }
   return *Publics;
 }
+
+Expected<SymbolStream &> PDBFile::getPDBSymbolStream() {
+  if (!Symbols) {
+    auto DbiS = getPDBDbiStream();
+    if (auto EC = DbiS.takeError())
+      return std::move(EC);
+    uint32_t SymbolStreamNum = DbiS->getSymRecordStreamIndex();
+
+    Symbols.reset(new SymbolStream(*this, SymbolStreamNum));
+    if (auto EC = Symbols->reload())
+      return std::move(EC);
+  }
+  return *Symbols;
+}
diff --git a/llvm/lib/DebugInfo/PDB/Raw/PublicsStream.cpp b/llvm/lib/DebugInfo/PDB/Raw/PublicsStream.cpp
index a8b78748866..2e0b8971f91 100644
--- a/llvm/lib/DebugInfo/PDB/Raw/PublicsStream.cpp
+++ b/llvm/lib/DebugInfo/PDB/Raw/PublicsStream.cpp
@@ -27,9 +27,11 @@
 #include "llvm/DebugInfo/CodeView/CodeView.h"
 #include "llvm/DebugInfo/CodeView/TypeRecord.h"
 #include "llvm/DebugInfo/PDB/Raw/MappedBlockStream.h"
+#include "llvm/DebugInfo/PDB/Raw/PDBFile.h"
 #include "llvm/DebugInfo/PDB/Raw/RawConstants.h"
 #include "llvm/DebugInfo/PDB/Raw/RawError.h"
 #include "llvm/DebugInfo/PDB/Raw/StreamReader.h"
+#include "llvm/DebugInfo/PDB/Raw/SymbolStream.h"
 
 #include "llvm/ADT/BitVector.h"
 #include "llvm/Support/Endian.h"
@@ -56,8 +58,7 @@ struct PublicsStream::HeaderInfo {
   ulittle32_t NumSections;
 };
 
-
-// This is GSIHashHdr struct defined in
+// This is GSIHashHdr.
 struct PublicsStream::GSIHashHeader {
   enum : unsigned {
     HdrSignature = ~0U,
@@ -69,8 +70,9 @@ struct PublicsStream::GSIHashHeader {
   ulittle32_t NumBuckets;
 };
 
-struct PublicsStream::HRFile {
-  ulittle32_t Off;
+// This is HRFile.
+struct PublicsStream::HashRecord {
+  ulittle32_t Off; // Offset in the symbol record stream
   ulittle32_t CRef;
 };
 
@@ -84,7 +86,7 @@ struct SectionOffset {
 }
 
 PublicsStream::PublicsStream(PDBFile &File, uint32_t StreamNum)
-    : StreamNum(StreamNum), Stream(StreamNum, File) {}
+    : Pdb(File), StreamNum(StreamNum), Stream(StreamNum, File) {}
 
 PublicsStream::~PublicsStream() {}
 
@@ -114,12 +116,12 @@ Error PublicsStream::reload() {
     return make_error<RawError>(raw_error_code::corrupt_file,
                                 "Publics Stream does not contain a header.");
 
-  // An array of HRFile follows. Read them.
-  if (HashHdr->HrSize % sizeof(HRFile))
+  // An array of HashRecord follows. Read them.
+  if (HashHdr->HrSize % sizeof(HashRecord))
     return make_error<RawError>(raw_error_code::corrupt_file,
                                 "Invalid HR array size.");
-  std::vector<HRFile> HRs(HashHdr->HrSize / sizeof(HRFile));
-  if (auto EC = Reader.readArray<HRFile>(HRs))
+  HashRecords.resize(HashHdr->HrSize / sizeof(HashRecord));
+  if (auto EC = Reader.readArray<HashRecord>(HashRecords))
     return make_error<RawError>(raw_error_code::corrupt_file,
                                 "Could not read an HR array");
 
@@ -178,3 +180,20 @@ Error PublicsStream::reload() {
                                 "Corrupted publics stream.");
   return Error::success();
 }
+
+std::vector<std::string> PublicsStream::getSymbols() const {
+  auto SymbolS = Pdb.getPDBSymbolStream();
+  if (SymbolS.takeError())
+    return {};
+  SymbolStream &SS = SymbolS.get();
+
+  std::vector<std::string> Ret;
+  for (const HashRecord &HR : HashRecords) {
+    // For some reason, symbol offset is biased by one.
+    Expected<std::string> Name = SS.getSymbolName(HR.Off - 1);
+    if (Name.takeError())
+      return Ret;
+    Ret.push_back(std::move(Name.get()));
+  }
+  return Ret;
+}
diff --git a/llvm/lib/DebugInfo/PDB/Raw/SymbolStream.cpp b/llvm/lib/DebugInfo/PDB/Raw/SymbolStream.cpp
new file mode 100644
index 00000000000..adf5412e8ca
--- /dev/null
+++ b/llvm/lib/DebugInfo/PDB/Raw/SymbolStream.cpp
@@ -0,0 +1,85 @@
+//===- SymbolStream.cpp - PDB Symbol Stream Access ------------------------===//
+//
+//                     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/SymbolStream.h"
+
+#include "llvm/DebugInfo/CodeView/CodeView.h"
+#include "llvm/DebugInfo/CodeView/TypeRecord.h"
+#include "llvm/DebugInfo/PDB/Raw/MappedBlockStream.h"
+#include "llvm/DebugInfo/PDB/Raw/RawConstants.h"
+#include "llvm/DebugInfo/PDB/Raw/RawError.h"
+#include "llvm/DebugInfo/PDB/Raw/StreamReader.h"
+
+#include "llvm/Support/Endian.h"
+
+using namespace llvm;
+using namespace llvm::support;
+using namespace llvm::pdb;
+
+// Symbol stream is an array of symbol records. Each record starts with
+// length and type fields followed by type-specfic fields.
+namespace {
+struct SymbolHeader {
+  ulittle16_t Len; // Record length
+  ulittle16_t Type;
+};
+
+// For S_PUB32 symbol type.
+struct DataSym32 {
+  ulittle32_t TypIndex; // Type index, or Metadata token if a managed symbol
+  ulittle32_t off;
+  ulittle16_t seg;
+  char name[1];
+};
+
+// For S_PROCREF symbol type.
+struct RefSym {
+  ulittle32_t SumName;   // SUC of the name (?)
+  ulittle32_t SymOffset; // Offset of actual symbol in $$Symbols
+  ulittle16_t Mod;       // Module containing the actual symbol
+  char name[1];
+};
+}
+
+SymbolStream::SymbolStream(PDBFile &File, uint32_t StreamNum)
+    : Stream(StreamNum, File) {}
+
+SymbolStream::~SymbolStream() {}
+
+Error SymbolStream::reload() { return Error::success(); }
+
+static StringRef makeStringRef(char *p) { return {p, strlen(p)}; }
+
+Expected<std::string> SymbolStream::getSymbolName(uint32_t Off) const {
+  StreamReader Reader(Stream);
+  Reader.setOffset(Off);
+
+  // Read length field.
+  SymbolHeader Hdr;
+  if (Reader.readObject(&Hdr))
+    return make_error<RawError>(raw_error_code::corrupt_file,
+                                "Corrupted symbol stream.");
+
+  // Read the entire record.
+  std::vector<uint8_t> Buf(Hdr.Len - sizeof(Hdr.Type));
+  if (Reader.readBytes(Buf))
+    return make_error<RawError>(raw_error_code::corrupt_file,
+                                "Corrupted symbol stream.");
+
+  switch (Hdr.Type) {
+  case codeview::S_PUB32:
+    return makeStringRef(reinterpret_cast<DataSym32 *>(Buf.data())->name);
+  case codeview::S_PROCREF:
+    return makeStringRef(reinterpret_cast<RefSym *>(Buf.data())->name);
+  default:
+    return make_error<RawError>(raw_error_code::corrupt_file,
+                                "Unknown symbol type");
+  }
+  return Error::success();
+}