Initial check in
Bug: 137197907
diff --git a/src/llvm-project/llvm/lib/DebugInfo/Symbolize/CMakeLists.txt b/src/llvm-project/llvm/lib/DebugInfo/Symbolize/CMakeLists.txt
new file mode 100644
index 0000000..fe5c4bf
--- /dev/null
+++ b/src/llvm-project/llvm/lib/DebugInfo/Symbolize/CMakeLists.txt
@@ -0,0 +1,8 @@
+add_llvm_library(LLVMSymbolize
+ DIPrinter.cpp
+ SymbolizableObjectFile.cpp
+ Symbolize.cpp
+
+ ADDITIONAL_HEADER_DIRS
+ ${LLVM_MAIN_INCLUDE_DIR}/llvm/DebugInfo/Symbolize
+ )
diff --git a/src/llvm-project/llvm/lib/DebugInfo/Symbolize/DIPrinter.cpp b/src/llvm-project/llvm/lib/DebugInfo/Symbolize/DIPrinter.cpp
new file mode 100644
index 0000000..c1e2536
--- /dev/null
+++ b/src/llvm-project/llvm/lib/DebugInfo/Symbolize/DIPrinter.cpp
@@ -0,0 +1,121 @@
+//===- lib/DebugInfo/Symbolize/DIPrinter.cpp ------------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines the DIPrinter class, which is responsible for printing
+// structures defined in DebugInfo/DIContext.h
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/DebugInfo/Symbolize/DIPrinter.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/DebugInfo/DIContext.h"
+#include "llvm/Support/ErrorOr.h"
+#include "llvm/Support/Format.h"
+#include "llvm/Support/LineIterator.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/raw_ostream.h"
+#include <algorithm>
+#include <cmath>
+#include <cstddef>
+#include <cstdint>
+#include <memory>
+#include <string>
+
+namespace llvm {
+namespace symbolize {
+
+// By default, DILineInfo contains "<invalid>" for function/filename it
+// cannot fetch. We replace it to "??" to make our output closer to addr2line.
+static const char kDILineInfoBadString[] = "<invalid>";
+static const char kBadString[] = "??";
+
+// Prints source code around in the FileName the Line.
+void DIPrinter::printContext(const std::string &FileName, int64_t Line) {
+ if (PrintSourceContext <= 0)
+ return;
+
+ ErrorOr<std::unique_ptr<MemoryBuffer>> BufOrErr =
+ MemoryBuffer::getFile(FileName);
+ if (!BufOrErr)
+ return;
+
+ std::unique_ptr<MemoryBuffer> Buf = std::move(BufOrErr.get());
+ int64_t FirstLine =
+ std::max(static_cast<int64_t>(1), Line - PrintSourceContext / 2);
+ int64_t LastLine = FirstLine + PrintSourceContext;
+ size_t MaxLineNumberWidth = std::ceil(std::log10(LastLine));
+
+ for (line_iterator I = line_iterator(*Buf, false);
+ !I.is_at_eof() && I.line_number() <= LastLine; ++I) {
+ int64_t L = I.line_number();
+ if (L >= FirstLine && L <= LastLine) {
+ OS << format_decimal(L, MaxLineNumberWidth);
+ if (L == Line)
+ OS << " >: ";
+ else
+ OS << " : ";
+ OS << *I << "\n";
+ }
+ }
+}
+
+void DIPrinter::print(const DILineInfo &Info, bool Inlined) {
+ if (PrintFunctionNames) {
+ std::string FunctionName = Info.FunctionName;
+ if (FunctionName == kDILineInfoBadString)
+ FunctionName = kBadString;
+
+ StringRef Delimiter = PrintPretty ? " at " : "\n";
+ StringRef Prefix = (PrintPretty && Inlined) ? " (inlined by) " : "";
+ OS << Prefix << FunctionName << Delimiter;
+ }
+ std::string Filename = Info.FileName;
+ if (Filename == kDILineInfoBadString)
+ Filename = kBadString;
+ if (!Verbose) {
+ OS << Filename << ":" << Info.Line << ":" << Info.Column << "\n";
+ printContext(Filename, Info.Line);
+ return;
+ }
+ OS << " Filename: " << Filename << "\n";
+ if (Info.StartLine)
+ OS << "Function start line: " << Info.StartLine << "\n";
+ OS << " Line: " << Info.Line << "\n";
+ OS << " Column: " << Info.Column << "\n";
+ if (Info.Discriminator)
+ OS << " Discriminator: " << Info.Discriminator << "\n";
+}
+
+DIPrinter &DIPrinter::operator<<(const DILineInfo &Info) {
+ print(Info, false);
+ return *this;
+}
+
+DIPrinter &DIPrinter::operator<<(const DIInliningInfo &Info) {
+ uint32_t FramesNum = Info.getNumberOfFrames();
+ if (FramesNum == 0) {
+ print(DILineInfo(), false);
+ return *this;
+ }
+ for (uint32_t i = 0; i < FramesNum; i++)
+ print(Info.getFrame(i), i > 0);
+ return *this;
+}
+
+DIPrinter &DIPrinter::operator<<(const DIGlobal &Global) {
+ std::string Name = Global.Name;
+ if (Name == kDILineInfoBadString)
+ Name = kBadString;
+ OS << Name << "\n";
+ OS << Global.Start << " " << Global.Size << "\n";
+ return *this;
+}
+
+} // end namespace symbolize
+} // end namespace llvm
diff --git a/src/llvm-project/llvm/lib/DebugInfo/Symbolize/LLVMBuild.txt b/src/llvm-project/llvm/lib/DebugInfo/Symbolize/LLVMBuild.txt
new file mode 100644
index 0000000..06498a8
--- /dev/null
+++ b/src/llvm-project/llvm/lib/DebugInfo/Symbolize/LLVMBuild.txt
@@ -0,0 +1,22 @@
+;===- ./lib/DebugInfo/Symbolize/LLVMBuild.txt ------------------*- Conf -*--===;
+;
+; The LLVM Compiler Infrastructure
+;
+; This file is distributed under the University of Illinois Open Source
+; License. See LICENSE.TXT for details.
+;
+;===------------------------------------------------------------------------===;
+;
+; This is an LLVMBuild description file for the components in this subdirectory.
+;
+; For more information on the LLVMBuild system, please see:
+;
+; http://llvm.org/docs/LLVMBuild.html
+;
+;===------------------------------------------------------------------------===;
+
+[component_0]
+type = Library
+name = Symbolize
+parent = DebugInfo
+required_libraries = DebugInfoDWARF DebugInfoPDB Object Support Demangle
diff --git a/src/llvm-project/llvm/lib/DebugInfo/Symbolize/SymbolizableObjectFile.cpp b/src/llvm-project/llvm/lib/DebugInfo/Symbolize/SymbolizableObjectFile.cpp
new file mode 100644
index 0000000..08be524
--- /dev/null
+++ b/src/llvm-project/llvm/lib/DebugInfo/Symbolize/SymbolizableObjectFile.cpp
@@ -0,0 +1,271 @@
+//===- SymbolizableObjectFile.cpp -----------------------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// Implementation of SymbolizableObjectFile class.
+//
+//===----------------------------------------------------------------------===//
+
+#include "SymbolizableObjectFile.h"
+#include "llvm/ADT/STLExtras.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/ADT/Triple.h"
+#include "llvm/BinaryFormat/COFF.h"
+#include "llvm/DebugInfo/DWARF/DWARFContext.h"
+#include "llvm/DebugInfo/Symbolize/SymbolizableModule.h"
+#include "llvm/Object/COFF.h"
+#include "llvm/Object/ObjectFile.h"
+#include "llvm/Object/SymbolSize.h"
+#include "llvm/Support/Casting.h"
+#include "llvm/Support/DataExtractor.h"
+#include "llvm/Support/Error.h"
+#include <algorithm>
+#include <cstdint>
+#include <memory>
+#include <string>
+#include <system_error>
+#include <utility>
+#include <vector>
+
+using namespace llvm;
+using namespace object;
+using namespace symbolize;
+
+static DILineInfoSpecifier
+getDILineInfoSpecifier(FunctionNameKind FNKind) {
+ return DILineInfoSpecifier(
+ DILineInfoSpecifier::FileLineInfoKind::AbsoluteFilePath, FNKind);
+}
+
+ErrorOr<std::unique_ptr<SymbolizableObjectFile>>
+SymbolizableObjectFile::create(object::ObjectFile *Obj,
+ std::unique_ptr<DIContext> DICtx) {
+ std::unique_ptr<SymbolizableObjectFile> res(
+ new SymbolizableObjectFile(Obj, std::move(DICtx)));
+ std::unique_ptr<DataExtractor> OpdExtractor;
+ uint64_t OpdAddress = 0;
+ // Find the .opd (function descriptor) section if any, for big-endian
+ // PowerPC64 ELF.
+ if (Obj->getArch() == Triple::ppc64) {
+ for (section_iterator Section : Obj->sections()) {
+ StringRef Name;
+ StringRef Data;
+ if (auto EC = Section->getName(Name))
+ return EC;
+ if (Name == ".opd") {
+ if (auto EC = Section->getContents(Data))
+ return EC;
+ OpdExtractor.reset(new DataExtractor(Data, Obj->isLittleEndian(),
+ Obj->getBytesInAddress()));
+ OpdAddress = Section->getAddress();
+ break;
+ }
+ }
+ }
+ std::vector<std::pair<SymbolRef, uint64_t>> Symbols =
+ computeSymbolSizes(*Obj);
+ for (auto &P : Symbols)
+ res->addSymbol(P.first, P.second, OpdExtractor.get(), OpdAddress);
+
+ // If this is a COFF object and we didn't find any symbols, try the export
+ // table.
+ if (Symbols.empty()) {
+ if (auto *CoffObj = dyn_cast<COFFObjectFile>(Obj))
+ if (auto EC = res->addCoffExportSymbols(CoffObj))
+ return EC;
+ }
+ return std::move(res);
+}
+
+SymbolizableObjectFile::SymbolizableObjectFile(ObjectFile *Obj,
+ std::unique_ptr<DIContext> DICtx)
+ : Module(Obj), DebugInfoContext(std::move(DICtx)) {}
+
+namespace {
+
+struct OffsetNamePair {
+ uint32_t Offset;
+ StringRef Name;
+
+ bool operator<(const OffsetNamePair &R) const {
+ return Offset < R.Offset;
+ }
+};
+
+} // end anonymous namespace
+
+std::error_code SymbolizableObjectFile::addCoffExportSymbols(
+ const COFFObjectFile *CoffObj) {
+ // Get all export names and offsets.
+ std::vector<OffsetNamePair> ExportSyms;
+ for (const ExportDirectoryEntryRef &Ref : CoffObj->export_directories()) {
+ StringRef Name;
+ uint32_t Offset;
+ if (auto EC = Ref.getSymbolName(Name))
+ return EC;
+ if (auto EC = Ref.getExportRVA(Offset))
+ return EC;
+ ExportSyms.push_back(OffsetNamePair{Offset, Name});
+ }
+ if (ExportSyms.empty())
+ return std::error_code();
+
+ // Sort by ascending offset.
+ array_pod_sort(ExportSyms.begin(), ExportSyms.end());
+
+ // Approximate the symbol sizes by assuming they run to the next symbol.
+ // FIXME: This assumes all exports are functions.
+ uint64_t ImageBase = CoffObj->getImageBase();
+ for (auto I = ExportSyms.begin(), E = ExportSyms.end(); I != E; ++I) {
+ OffsetNamePair &Export = *I;
+ // FIXME: The last export has a one byte size now.
+ uint32_t NextOffset = I != E ? I->Offset : Export.Offset + 1;
+ uint64_t SymbolStart = ImageBase + Export.Offset;
+ uint64_t SymbolSize = NextOffset - Export.Offset;
+ SymbolDesc SD = {SymbolStart, SymbolSize};
+ Functions.insert(std::make_pair(SD, Export.Name));
+ }
+ return std::error_code();
+}
+
+std::error_code SymbolizableObjectFile::addSymbol(const SymbolRef &Symbol,
+ uint64_t SymbolSize,
+ DataExtractor *OpdExtractor,
+ uint64_t OpdAddress) {
+ Expected<SymbolRef::Type> SymbolTypeOrErr = Symbol.getType();
+ if (!SymbolTypeOrErr)
+ return errorToErrorCode(SymbolTypeOrErr.takeError());
+ SymbolRef::Type SymbolType = *SymbolTypeOrErr;
+ if (SymbolType != SymbolRef::ST_Function && SymbolType != SymbolRef::ST_Data)
+ return std::error_code();
+ Expected<uint64_t> SymbolAddressOrErr = Symbol.getAddress();
+ if (!SymbolAddressOrErr)
+ return errorToErrorCode(SymbolAddressOrErr.takeError());
+ uint64_t SymbolAddress = *SymbolAddressOrErr;
+ if (OpdExtractor) {
+ // For big-endian PowerPC64 ELF, symbols in the .opd section refer to
+ // function descriptors. The first word of the descriptor is a pointer to
+ // the function's code.
+ // For the purposes of symbolization, pretend the symbol's address is that
+ // of the function's code, not the descriptor.
+ uint64_t OpdOffset = SymbolAddress - OpdAddress;
+ uint32_t OpdOffset32 = OpdOffset;
+ if (OpdOffset == OpdOffset32 &&
+ OpdExtractor->isValidOffsetForAddress(OpdOffset32))
+ SymbolAddress = OpdExtractor->getAddress(&OpdOffset32);
+ }
+ Expected<StringRef> SymbolNameOrErr = Symbol.getName();
+ if (!SymbolNameOrErr)
+ return errorToErrorCode(SymbolNameOrErr.takeError());
+ StringRef SymbolName = *SymbolNameOrErr;
+ // Mach-O symbol table names have leading underscore, skip it.
+ if (Module->isMachO() && !SymbolName.empty() && SymbolName[0] == '_')
+ SymbolName = SymbolName.drop_front();
+ // FIXME: If a function has alias, there are two entries in symbol table
+ // with same address size. Make sure we choose the correct one.
+ auto &M = SymbolType == SymbolRef::ST_Function ? Functions : Objects;
+ SymbolDesc SD = { SymbolAddress, SymbolSize };
+ M.insert(std::make_pair(SD, SymbolName));
+ return std::error_code();
+}
+
+// Return true if this is a 32-bit x86 PE COFF module.
+bool SymbolizableObjectFile::isWin32Module() const {
+ auto *CoffObject = dyn_cast<COFFObjectFile>(Module);
+ return CoffObject && CoffObject->getMachine() == COFF::IMAGE_FILE_MACHINE_I386;
+}
+
+uint64_t SymbolizableObjectFile::getModulePreferredBase() const {
+ if (auto *CoffObject = dyn_cast<COFFObjectFile>(Module))
+ return CoffObject->getImageBase();
+ return 0;
+}
+
+bool SymbolizableObjectFile::getNameFromSymbolTable(SymbolRef::Type Type,
+ uint64_t Address,
+ std::string &Name,
+ uint64_t &Addr,
+ uint64_t &Size) const {
+ const auto &SymbolMap = Type == SymbolRef::ST_Function ? Functions : Objects;
+ if (SymbolMap.empty())
+ return false;
+ SymbolDesc SD = { Address, Address };
+ auto SymbolIterator = SymbolMap.upper_bound(SD);
+ if (SymbolIterator == SymbolMap.begin())
+ return false;
+ --SymbolIterator;
+ if (SymbolIterator->first.Size != 0 &&
+ SymbolIterator->first.Addr + SymbolIterator->first.Size <= Address)
+ return false;
+ Name = SymbolIterator->second.str();
+ Addr = SymbolIterator->first.Addr;
+ Size = SymbolIterator->first.Size;
+ return true;
+}
+
+bool SymbolizableObjectFile::shouldOverrideWithSymbolTable(
+ FunctionNameKind FNKind, bool UseSymbolTable) const {
+ // When DWARF is used with -gline-tables-only / -gmlt, the symbol table gives
+ // better answers for linkage names than the DIContext. Otherwise, we are
+ // probably using PEs and PDBs, and we shouldn't do the override. PE files
+ // generally only contain the names of exported symbols.
+ return FNKind == FunctionNameKind::LinkageName && UseSymbolTable &&
+ isa<DWARFContext>(DebugInfoContext.get());
+}
+
+DILineInfo SymbolizableObjectFile::symbolizeCode(uint64_t ModuleOffset,
+ FunctionNameKind FNKind,
+ bool UseSymbolTable) const {
+ DILineInfo LineInfo;
+ if (DebugInfoContext) {
+ LineInfo = DebugInfoContext->getLineInfoForAddress(
+ ModuleOffset, getDILineInfoSpecifier(FNKind));
+ }
+ // Override function name from symbol table if necessary.
+ if (shouldOverrideWithSymbolTable(FNKind, UseSymbolTable)) {
+ std::string FunctionName;
+ uint64_t Start, Size;
+ if (getNameFromSymbolTable(SymbolRef::ST_Function, ModuleOffset,
+ FunctionName, Start, Size)) {
+ LineInfo.FunctionName = FunctionName;
+ }
+ }
+ return LineInfo;
+}
+
+DIInliningInfo SymbolizableObjectFile::symbolizeInlinedCode(
+ uint64_t ModuleOffset, FunctionNameKind FNKind, bool UseSymbolTable) const {
+ DIInliningInfo InlinedContext;
+
+ if (DebugInfoContext)
+ InlinedContext = DebugInfoContext->getInliningInfoForAddress(
+ ModuleOffset, getDILineInfoSpecifier(FNKind));
+ // Make sure there is at least one frame in context.
+ if (InlinedContext.getNumberOfFrames() == 0)
+ InlinedContext.addFrame(DILineInfo());
+
+ // Override the function name in lower frame with name from symbol table.
+ if (shouldOverrideWithSymbolTable(FNKind, UseSymbolTable)) {
+ std::string FunctionName;
+ uint64_t Start, Size;
+ if (getNameFromSymbolTable(SymbolRef::ST_Function, ModuleOffset,
+ FunctionName, Start, Size)) {
+ InlinedContext.getMutableFrame(InlinedContext.getNumberOfFrames() - 1)
+ ->FunctionName = FunctionName;
+ }
+ }
+
+ return InlinedContext;
+}
+
+DIGlobal SymbolizableObjectFile::symbolizeData(uint64_t ModuleOffset) const {
+ DIGlobal Res;
+ getNameFromSymbolTable(SymbolRef::ST_Data, ModuleOffset, Res.Name, Res.Start,
+ Res.Size);
+ return Res;
+}
diff --git a/src/llvm-project/llvm/lib/DebugInfo/Symbolize/SymbolizableObjectFile.h b/src/llvm-project/llvm/lib/DebugInfo/Symbolize/SymbolizableObjectFile.h
new file mode 100644
index 0000000..216cca8
--- /dev/null
+++ b/src/llvm-project/llvm/lib/DebugInfo/Symbolize/SymbolizableObjectFile.h
@@ -0,0 +1,90 @@
+//===- SymbolizableObjectFile.h ---------------------------------*- C++ -*-===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file declares the SymbolizableObjectFile class.
+//
+//===----------------------------------------------------------------------===//
+#ifndef LLVM_LIB_DEBUGINFO_SYMBOLIZE_SYMBOLIZABLEOBJECTFILE_H
+#define LLVM_LIB_DEBUGINFO_SYMBOLIZE_SYMBOLIZABLEOBJECTFILE_H
+
+#include "llvm/ADT/StringRef.h"
+#include "llvm/DebugInfo/DIContext.h"
+#include "llvm/DebugInfo/Symbolize/SymbolizableModule.h"
+#include "llvm/Support/ErrorOr.h"
+#include <cstdint>
+#include <map>
+#include <memory>
+#include <string>
+#include <system_error>
+
+namespace llvm {
+
+class DataExtractor;
+
+namespace symbolize {
+
+class SymbolizableObjectFile : public SymbolizableModule {
+public:
+ static ErrorOr<std::unique_ptr<SymbolizableObjectFile>>
+ create(object::ObjectFile *Obj, std::unique_ptr<DIContext> DICtx);
+
+ DILineInfo symbolizeCode(uint64_t ModuleOffset, FunctionNameKind FNKind,
+ bool UseSymbolTable) const override;
+ DIInliningInfo symbolizeInlinedCode(uint64_t ModuleOffset,
+ FunctionNameKind FNKind,
+ bool UseSymbolTable) const override;
+ DIGlobal symbolizeData(uint64_t ModuleOffset) const override;
+
+ // Return true if this is a 32-bit x86 PE COFF module.
+ bool isWin32Module() const override;
+
+ // Returns the preferred base of the module, i.e. where the loader would place
+ // it in memory assuming there were no conflicts.
+ uint64_t getModulePreferredBase() const override;
+
+private:
+ bool shouldOverrideWithSymbolTable(FunctionNameKind FNKind,
+ bool UseSymbolTable) const;
+
+ bool getNameFromSymbolTable(object::SymbolRef::Type Type, uint64_t Address,
+ std::string &Name, uint64_t &Addr,
+ uint64_t &Size) const;
+ // For big-endian PowerPC64 ELF, OpdAddress is the address of the .opd
+ // (function descriptor) section and OpdExtractor refers to its contents.
+ std::error_code addSymbol(const object::SymbolRef &Symbol,
+ uint64_t SymbolSize,
+ DataExtractor *OpdExtractor = nullptr,
+ uint64_t OpdAddress = 0);
+ std::error_code addCoffExportSymbols(const object::COFFObjectFile *CoffObj);
+
+ object::ObjectFile *Module;
+ std::unique_ptr<DIContext> DebugInfoContext;
+
+ struct SymbolDesc {
+ uint64_t Addr;
+ // If size is 0, assume that symbol occupies the whole memory range up to
+ // the following symbol.
+ uint64_t Size;
+
+ friend bool operator<(const SymbolDesc &s1, const SymbolDesc &s2) {
+ return s1.Addr < s2.Addr;
+ }
+ };
+ std::map<SymbolDesc, StringRef> Functions;
+ std::map<SymbolDesc, StringRef> Objects;
+
+ SymbolizableObjectFile(object::ObjectFile *Obj,
+ std::unique_ptr<DIContext> DICtx);
+};
+
+} // end namespace symbolize
+
+} // end namespace llvm
+
+#endif // LLVM_LIB_DEBUGINFO_SYMBOLIZE_SYMBOLIZABLEOBJECTFILE_H
diff --git a/src/llvm-project/llvm/lib/DebugInfo/Symbolize/Symbolize.cpp b/src/llvm-project/llvm/lib/DebugInfo/Symbolize/Symbolize.cpp
new file mode 100644
index 0000000..59a85d6
--- /dev/null
+++ b/src/llvm-project/llvm/lib/DebugInfo/Symbolize/Symbolize.cpp
@@ -0,0 +1,505 @@
+//===-- LLVMSymbolize.cpp -------------------------------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// Implementation for LLVM symbolization library.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/DebugInfo/Symbolize/Symbolize.h"
+
+#include "SymbolizableObjectFile.h"
+
+#include "llvm/ADT/STLExtras.h"
+#include "llvm/BinaryFormat/COFF.h"
+#include "llvm/Config/config.h"
+#include "llvm/DebugInfo/DWARF/DWARFContext.h"
+#include "llvm/DebugInfo/PDB/PDB.h"
+#include "llvm/DebugInfo/PDB/PDBContext.h"
+#include "llvm/Demangle/Demangle.h"
+#include "llvm/Object/COFF.h"
+#include "llvm/Object/MachO.h"
+#include "llvm/Object/MachOUniversal.h"
+#include "llvm/Support/Casting.h"
+#include "llvm/Support/Compression.h"
+#include "llvm/Support/DataExtractor.h"
+#include "llvm/Support/Errc.h"
+#include "llvm/Support/FileSystem.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/Path.h"
+#include <algorithm>
+#include <cassert>
+#include <cstdlib>
+#include <cstring>
+
+#if defined(_MSC_VER)
+#include <Windows.h>
+
+// This must be included after windows.h.
+#include <DbgHelp.h>
+#pragma comment(lib, "dbghelp.lib")
+
+// Windows.h conflicts with our COFF header definitions.
+#ifdef IMAGE_FILE_MACHINE_I386
+#undef IMAGE_FILE_MACHINE_I386
+#endif
+#endif
+
+namespace llvm {
+namespace symbolize {
+
+Expected<DILineInfo>
+LLVMSymbolizer::symbolizeCode(const std::string &ModuleName,
+ uint64_t ModuleOffset, StringRef DWPName) {
+ SymbolizableModule *Info;
+ if (auto InfoOrErr = getOrCreateModuleInfo(ModuleName, DWPName))
+ Info = InfoOrErr.get();
+ else
+ return InfoOrErr.takeError();
+
+ // A null module means an error has already been reported. Return an empty
+ // result.
+ if (!Info)
+ return DILineInfo();
+
+ // If the user is giving us relative addresses, add the preferred base of the
+ // object to the offset before we do the query. It's what DIContext expects.
+ if (Opts.RelativeAddresses)
+ ModuleOffset += Info->getModulePreferredBase();
+
+ DILineInfo LineInfo = Info->symbolizeCode(ModuleOffset, Opts.PrintFunctions,
+ Opts.UseSymbolTable);
+ if (Opts.Demangle)
+ LineInfo.FunctionName = DemangleName(LineInfo.FunctionName, Info);
+ return LineInfo;
+}
+
+Expected<DIInliningInfo>
+LLVMSymbolizer::symbolizeInlinedCode(const std::string &ModuleName,
+ uint64_t ModuleOffset, StringRef DWPName) {
+ SymbolizableModule *Info;
+ if (auto InfoOrErr = getOrCreateModuleInfo(ModuleName, DWPName))
+ Info = InfoOrErr.get();
+ else
+ return InfoOrErr.takeError();
+
+ // A null module means an error has already been reported. Return an empty
+ // result.
+ if (!Info)
+ return DIInliningInfo();
+
+ // If the user is giving us relative addresses, add the preferred base of the
+ // object to the offset before we do the query. It's what DIContext expects.
+ if (Opts.RelativeAddresses)
+ ModuleOffset += Info->getModulePreferredBase();
+
+ DIInliningInfo InlinedContext = Info->symbolizeInlinedCode(
+ ModuleOffset, Opts.PrintFunctions, Opts.UseSymbolTable);
+ if (Opts.Demangle) {
+ for (int i = 0, n = InlinedContext.getNumberOfFrames(); i < n; i++) {
+ auto *Frame = InlinedContext.getMutableFrame(i);
+ Frame->FunctionName = DemangleName(Frame->FunctionName, Info);
+ }
+ }
+ return InlinedContext;
+}
+
+Expected<DIGlobal> LLVMSymbolizer::symbolizeData(const std::string &ModuleName,
+ uint64_t ModuleOffset) {
+ SymbolizableModule *Info;
+ if (auto InfoOrErr = getOrCreateModuleInfo(ModuleName))
+ Info = InfoOrErr.get();
+ else
+ return InfoOrErr.takeError();
+
+ // A null module means an error has already been reported. Return an empty
+ // result.
+ if (!Info)
+ return DIGlobal();
+
+ // If the user is giving us relative addresses, add the preferred base of
+ // the object to the offset before we do the query. It's what DIContext
+ // expects.
+ if (Opts.RelativeAddresses)
+ ModuleOffset += Info->getModulePreferredBase();
+
+ DIGlobal Global = Info->symbolizeData(ModuleOffset);
+ if (Opts.Demangle)
+ Global.Name = DemangleName(Global.Name, Info);
+ return Global;
+}
+
+void LLVMSymbolizer::flush() {
+ ObjectForUBPathAndArch.clear();
+ BinaryForPath.clear();
+ ObjectPairForPathArch.clear();
+ Modules.clear();
+}
+
+namespace {
+
+// For Path="/path/to/foo" and Basename="foo" assume that debug info is in
+// /path/to/foo.dSYM/Contents/Resources/DWARF/foo.
+// For Path="/path/to/bar.dSYM" and Basename="foo" assume that debug info is in
+// /path/to/bar.dSYM/Contents/Resources/DWARF/foo.
+std::string getDarwinDWARFResourceForPath(
+ const std::string &Path, const std::string &Basename) {
+ SmallString<16> ResourceName = StringRef(Path);
+ if (sys::path::extension(Path) != ".dSYM") {
+ ResourceName += ".dSYM";
+ }
+ sys::path::append(ResourceName, "Contents", "Resources", "DWARF");
+ sys::path::append(ResourceName, Basename);
+ return ResourceName.str();
+}
+
+bool checkFileCRC(StringRef Path, uint32_t CRCHash) {
+ ErrorOr<std::unique_ptr<MemoryBuffer>> MB =
+ MemoryBuffer::getFileOrSTDIN(Path);
+ if (!MB)
+ return false;
+ return !zlib::isAvailable() || CRCHash == zlib::crc32(MB.get()->getBuffer());
+}
+
+bool findDebugBinary(const std::string &OrigPath,
+ const std::string &DebuglinkName, uint32_t CRCHash,
+ std::string &Result) {
+ std::string OrigRealPath = OrigPath;
+#if defined(HAVE_REALPATH)
+ if (char *RP = realpath(OrigPath.c_str(), nullptr)) {
+ OrigRealPath = RP;
+ free(RP);
+ }
+#endif
+ SmallString<16> OrigDir(OrigRealPath);
+ llvm::sys::path::remove_filename(OrigDir);
+ SmallString<16> DebugPath = OrigDir;
+ // Try /path/to/original_binary/debuglink_name
+ llvm::sys::path::append(DebugPath, DebuglinkName);
+ if (checkFileCRC(DebugPath, CRCHash)) {
+ Result = DebugPath.str();
+ return true;
+ }
+ // Try /path/to/original_binary/.debug/debuglink_name
+ DebugPath = OrigDir;
+ llvm::sys::path::append(DebugPath, ".debug", DebuglinkName);
+ if (checkFileCRC(DebugPath, CRCHash)) {
+ Result = DebugPath.str();
+ return true;
+ }
+#if defined(__NetBSD__)
+ // Try /usr/libdata/debug/path/to/original_binary/debuglink_name
+ DebugPath = "/usr/libdata/debug";
+#else
+ // Try /usr/lib/debug/path/to/original_binary/debuglink_name
+ DebugPath = "/usr/lib/debug";
+#endif
+ llvm::sys::path::append(DebugPath, llvm::sys::path::relative_path(OrigDir),
+ DebuglinkName);
+ if (checkFileCRC(DebugPath, CRCHash)) {
+ Result = DebugPath.str();
+ return true;
+ }
+ return false;
+}
+
+bool getGNUDebuglinkContents(const ObjectFile *Obj, std::string &DebugName,
+ uint32_t &CRCHash) {
+ if (!Obj)
+ return false;
+ for (const SectionRef &Section : Obj->sections()) {
+ StringRef Name;
+ Section.getName(Name);
+ Name = Name.substr(Name.find_first_not_of("._"));
+ if (Name == "gnu_debuglink") {
+ StringRef Data;
+ Section.getContents(Data);
+ DataExtractor DE(Data, Obj->isLittleEndian(), 0);
+ uint32_t Offset = 0;
+ if (const char *DebugNameStr = DE.getCStr(&Offset)) {
+ // 4-byte align the offset.
+ Offset = (Offset + 3) & ~0x3;
+ if (DE.isValidOffsetForDataOfSize(Offset, 4)) {
+ DebugName = DebugNameStr;
+ CRCHash = DE.getU32(&Offset);
+ return true;
+ }
+ }
+ break;
+ }
+ }
+ return false;
+}
+
+bool darwinDsymMatchesBinary(const MachOObjectFile *DbgObj,
+ const MachOObjectFile *Obj) {
+ ArrayRef<uint8_t> dbg_uuid = DbgObj->getUuid();
+ ArrayRef<uint8_t> bin_uuid = Obj->getUuid();
+ if (dbg_uuid.empty() || bin_uuid.empty())
+ return false;
+ return !memcmp(dbg_uuid.data(), bin_uuid.data(), dbg_uuid.size());
+}
+
+} // end anonymous namespace
+
+ObjectFile *LLVMSymbolizer::lookUpDsymFile(const std::string &ExePath,
+ const MachOObjectFile *MachExeObj, const std::string &ArchName) {
+ // On Darwin we may find DWARF in separate object file in
+ // resource directory.
+ std::vector<std::string> DsymPaths;
+ StringRef Filename = sys::path::filename(ExePath);
+ DsymPaths.push_back(getDarwinDWARFResourceForPath(ExePath, Filename));
+ for (const auto &Path : Opts.DsymHints) {
+ DsymPaths.push_back(getDarwinDWARFResourceForPath(Path, Filename));
+ }
+ for (const auto &Path : DsymPaths) {
+ auto DbgObjOrErr = getOrCreateObject(Path, ArchName);
+ if (!DbgObjOrErr) {
+ // Ignore errors, the file might not exist.
+ consumeError(DbgObjOrErr.takeError());
+ continue;
+ }
+ ObjectFile *DbgObj = DbgObjOrErr.get();
+ if (!DbgObj)
+ continue;
+ const MachOObjectFile *MachDbgObj = dyn_cast<const MachOObjectFile>(DbgObj);
+ if (!MachDbgObj)
+ continue;
+ if (darwinDsymMatchesBinary(MachDbgObj, MachExeObj))
+ return DbgObj;
+ }
+ return nullptr;
+}
+
+ObjectFile *LLVMSymbolizer::lookUpDebuglinkObject(const std::string &Path,
+ const ObjectFile *Obj,
+ const std::string &ArchName) {
+ std::string DebuglinkName;
+ uint32_t CRCHash;
+ std::string DebugBinaryPath;
+ if (!getGNUDebuglinkContents(Obj, DebuglinkName, CRCHash))
+ return nullptr;
+ if (!findDebugBinary(Path, DebuglinkName, CRCHash, DebugBinaryPath))
+ return nullptr;
+ auto DbgObjOrErr = getOrCreateObject(DebugBinaryPath, ArchName);
+ if (!DbgObjOrErr) {
+ // Ignore errors, the file might not exist.
+ consumeError(DbgObjOrErr.takeError());
+ return nullptr;
+ }
+ return DbgObjOrErr.get();
+}
+
+Expected<LLVMSymbolizer::ObjectPair>
+LLVMSymbolizer::getOrCreateObjectPair(const std::string &Path,
+ const std::string &ArchName) {
+ const auto &I = ObjectPairForPathArch.find(std::make_pair(Path, ArchName));
+ if (I != ObjectPairForPathArch.end()) {
+ return I->second;
+ }
+
+ auto ObjOrErr = getOrCreateObject(Path, ArchName);
+ if (!ObjOrErr) {
+ ObjectPairForPathArch.insert(std::make_pair(std::make_pair(Path, ArchName),
+ ObjectPair(nullptr, nullptr)));
+ return ObjOrErr.takeError();
+ }
+
+ ObjectFile *Obj = ObjOrErr.get();
+ assert(Obj != nullptr);
+ ObjectFile *DbgObj = nullptr;
+
+ if (auto MachObj = dyn_cast<const MachOObjectFile>(Obj))
+ DbgObj = lookUpDsymFile(Path, MachObj, ArchName);
+ if (!DbgObj)
+ DbgObj = lookUpDebuglinkObject(Path, Obj, ArchName);
+ if (!DbgObj)
+ DbgObj = Obj;
+ ObjectPair Res = std::make_pair(Obj, DbgObj);
+ ObjectPairForPathArch.insert(
+ std::make_pair(std::make_pair(Path, ArchName), Res));
+ return Res;
+}
+
+Expected<ObjectFile *>
+LLVMSymbolizer::getOrCreateObject(const std::string &Path,
+ const std::string &ArchName) {
+ const auto &I = BinaryForPath.find(Path);
+ Binary *Bin = nullptr;
+ if (I == BinaryForPath.end()) {
+ Expected<OwningBinary<Binary>> BinOrErr = createBinary(Path);
+ if (!BinOrErr) {
+ BinaryForPath.insert(std::make_pair(Path, OwningBinary<Binary>()));
+ return BinOrErr.takeError();
+ }
+ Bin = BinOrErr->getBinary();
+ BinaryForPath.insert(std::make_pair(Path, std::move(BinOrErr.get())));
+ } else {
+ Bin = I->second.getBinary();
+ }
+
+ if (!Bin)
+ return static_cast<ObjectFile *>(nullptr);
+
+ if (MachOUniversalBinary *UB = dyn_cast_or_null<MachOUniversalBinary>(Bin)) {
+ const auto &I = ObjectForUBPathAndArch.find(std::make_pair(Path, ArchName));
+ if (I != ObjectForUBPathAndArch.end()) {
+ return I->second.get();
+ }
+ Expected<std::unique_ptr<ObjectFile>> ObjOrErr =
+ UB->getObjectForArch(ArchName);
+ if (!ObjOrErr) {
+ ObjectForUBPathAndArch.insert(std::make_pair(
+ std::make_pair(Path, ArchName), std::unique_ptr<ObjectFile>()));
+ return ObjOrErr.takeError();
+ }
+ ObjectFile *Res = ObjOrErr->get();
+ ObjectForUBPathAndArch.insert(std::make_pair(std::make_pair(Path, ArchName),
+ std::move(ObjOrErr.get())));
+ return Res;
+ }
+ if (Bin->isObject()) {
+ return cast<ObjectFile>(Bin);
+ }
+ return errorCodeToError(object_error::arch_not_found);
+}
+
+Expected<SymbolizableModule *>
+LLVMSymbolizer::getOrCreateModuleInfo(const std::string &ModuleName,
+ StringRef DWPName) {
+ const auto &I = Modules.find(ModuleName);
+ if (I != Modules.end()) {
+ return I->second.get();
+ }
+ std::string BinaryName = ModuleName;
+ std::string ArchName = Opts.DefaultArch;
+ size_t ColonPos = ModuleName.find_last_of(':');
+ // Verify that substring after colon form a valid arch name.
+ if (ColonPos != std::string::npos) {
+ std::string ArchStr = ModuleName.substr(ColonPos + 1);
+ if (Triple(ArchStr).getArch() != Triple::UnknownArch) {
+ BinaryName = ModuleName.substr(0, ColonPos);
+ ArchName = ArchStr;
+ }
+ }
+ auto ObjectsOrErr = getOrCreateObjectPair(BinaryName, ArchName);
+ if (!ObjectsOrErr) {
+ // Failed to find valid object file.
+ Modules.insert(
+ std::make_pair(ModuleName, std::unique_ptr<SymbolizableModule>()));
+ return ObjectsOrErr.takeError();
+ }
+ ObjectPair Objects = ObjectsOrErr.get();
+
+ std::unique_ptr<DIContext> Context;
+ // If this is a COFF object containing PDB info, use a PDBContext to
+ // symbolize. Otherwise, use DWARF.
+ if (auto CoffObject = dyn_cast<COFFObjectFile>(Objects.first)) {
+ const codeview::DebugInfo *DebugInfo;
+ StringRef PDBFileName;
+ auto EC = CoffObject->getDebugPDBInfo(DebugInfo, PDBFileName);
+ if (!EC && DebugInfo != nullptr && !PDBFileName.empty()) {
+ using namespace pdb;
+ std::unique_ptr<IPDBSession> Session;
+ if (auto Err = loadDataForEXE(PDB_ReaderType::DIA,
+ Objects.first->getFileName(), Session)) {
+ Modules.insert(
+ std::make_pair(ModuleName, std::unique_ptr<SymbolizableModule>()));
+ // Return along the PDB filename to provide more context
+ return createFileError(PDBFileName, std::move(Err));
+ }
+ Context.reset(new PDBContext(*CoffObject, std::move(Session)));
+ }
+ }
+ if (!Context)
+ Context = DWARFContext::create(*Objects.second, nullptr,
+ DWARFContext::defaultErrorHandler, DWPName);
+ assert(Context);
+ auto InfoOrErr =
+ SymbolizableObjectFile::create(Objects.first, std::move(Context));
+ std::unique_ptr<SymbolizableModule> SymMod;
+ if (InfoOrErr)
+ SymMod = std::move(InfoOrErr.get());
+ auto InsertResult =
+ Modules.insert(std::make_pair(ModuleName, std::move(SymMod)));
+ assert(InsertResult.second);
+ if (auto EC = InfoOrErr.getError())
+ return errorCodeToError(EC);
+ return InsertResult.first->second.get();
+}
+
+namespace {
+
+// Undo these various manglings for Win32 extern "C" functions:
+// cdecl - _foo
+// stdcall - _foo@12
+// fastcall - @foo@12
+// vectorcall - foo@@12
+// These are all different linkage names for 'foo'.
+StringRef demanglePE32ExternCFunc(StringRef SymbolName) {
+ // Remove any '_' or '@' prefix.
+ char Front = SymbolName.empty() ? '\0' : SymbolName[0];
+ if (Front == '_' || Front == '@')
+ SymbolName = SymbolName.drop_front();
+
+ // Remove any '@[0-9]+' suffix.
+ if (Front != '?') {
+ size_t AtPos = SymbolName.rfind('@');
+ if (AtPos != StringRef::npos &&
+ std::all_of(SymbolName.begin() + AtPos + 1, SymbolName.end(),
+ [](char C) { return C >= '0' && C <= '9'; })) {
+ SymbolName = SymbolName.substr(0, AtPos);
+ }
+ }
+
+ // Remove any ending '@' for vectorcall.
+ if (SymbolName.endswith("@"))
+ SymbolName = SymbolName.drop_back();
+
+ return SymbolName;
+}
+
+} // end anonymous namespace
+
+std::string
+LLVMSymbolizer::DemangleName(const std::string &Name,
+ const SymbolizableModule *DbiModuleDescriptor) {
+ // We can spoil names of symbols with C linkage, so use an heuristic
+ // approach to check if the name should be demangled.
+ if (Name.substr(0, 2) == "_Z") {
+ int status = 0;
+ char *DemangledName = itaniumDemangle(Name.c_str(), nullptr, nullptr, &status);
+ if (status != 0)
+ return Name;
+ std::string Result = DemangledName;
+ free(DemangledName);
+ return Result;
+ }
+
+#if defined(_MSC_VER)
+ if (!Name.empty() && Name.front() == '?') {
+ // Only do MSVC C++ demangling on symbols starting with '?'.
+ char DemangledName[1024] = {0};
+ DWORD result = ::UnDecorateSymbolName(
+ Name.c_str(), DemangledName, 1023,
+ UNDNAME_NO_ACCESS_SPECIFIERS | // Strip public, private, protected
+ UNDNAME_NO_ALLOCATION_LANGUAGE | // Strip __thiscall, __stdcall, etc
+ UNDNAME_NO_THROW_SIGNATURES | // Strip throw() specifications
+ UNDNAME_NO_MEMBER_TYPE | // Strip virtual, static, etc specifiers
+ UNDNAME_NO_MS_KEYWORDS | // Strip all MS extension keywords
+ UNDNAME_NO_FUNCTION_RETURNS); // Strip function return types
+ return (result == 0) ? Name : std::string(DemangledName);
+ }
+#endif
+ if (DbiModuleDescriptor && DbiModuleDescriptor->isWin32Module())
+ return std::string(demanglePE32ExternCFunc(Name));
+ return Name;
+}
+
+} // namespace symbolize
+} // namespace llvm
