LLVM symbolizer gsym support (#134847)

Add support for gsym files to llvm-symbolizer.

co-author @sfc-gh-sgiesecke

---------

Co-authored-by: David Blaikie <dblaikie@gmail.com>

Author: sfc-gh-mkwiczala

llvm/include/llvm/DebugInfo/DIContext.h

@@ -238,7 +238,7 @@ struct DIDumpOptions {
 
 class DIContext {
 public:
-  enum DIContextKind { CK_DWARF, CK_PDB, CK_BTF };
+  enum DIContextKind { CK_DWARF, CK_PDB, CK_BTF, CK_GSYM };
 
   DIContext(DIContextKind K) : Kind(K) {}
   virtual ~DIContext() = default;

llvm/include/llvm/DebugInfo/GSYM/GsymDIContext.h

@@ -0,0 +1,66 @@
+//===-- GsymDIContext.h --------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===/
+
+#ifndef LLVM_DEBUGINFO_GSYM_GSYMDICONTEXT_H
+#define LLVM_DEBUGINFO_GSYM_GSYMDICONTEXT_H
+
+#include "llvm/DebugInfo/DIContext.h"
+#include <cstdint>
+#include <memory>
+#include <string>
+
+namespace llvm {
+
+namespace gsym {
+
+class GsymReader;
+
+/// GSYM DI Context
+/// This data structure is the top level entity that deals with GSYM
+/// symbolication.
+/// This data structure exists only when there is a need for a transparent
+/// interface to different symbolication formats (e.g. GSYM, PDB and DWARF).
+/// More control and power over the debug information access can be had by using
+/// the GSYM interfaces directly.
+class GsymDIContext : public DIContext {
+public:
+  GsymDIContext(std::unique_ptr<GsymReader> Reader);
+
+  GsymDIContext(GsymDIContext &) = delete;
+  GsymDIContext &operator=(GsymDIContext &) = delete;
+
+  static bool classof(const DIContext *DICtx) {
+    return DICtx->getKind() == CK_GSYM;
+  }
+
+  void dump(raw_ostream &OS, DIDumpOptions DIDumpOpts) override;
+
+  std::optional<DILineInfo> getLineInfoForAddress(
+      object::SectionedAddress Address,
+      DILineInfoSpecifier Specifier = DILineInfoSpecifier()) override;
+  std::optional<DILineInfo>
+  getLineInfoForDataAddress(object::SectionedAddress Address) override;
+  DILineInfoTable getLineInfoForAddressRange(
+      object::SectionedAddress Address, uint64_t Size,
+      DILineInfoSpecifier Specifier = DILineInfoSpecifier()) override;
+  DIInliningInfo getInliningInfoForAddress(
+      object::SectionedAddress Address,
+      DILineInfoSpecifier Specifier = DILineInfoSpecifier()) override;
+
+  std::vector<DILocal>
+  getLocalsForAddress(object::SectionedAddress Address) override;
+
+private:
+  const std::unique_ptr<GsymReader> Reader;
+};
+
+} // end namespace gsym
+
+} // end namespace llvm
+
+#endif // LLVM_DEBUGINFO_PDB_PDBCONTEXT_H

llvm/include/llvm/DebugInfo/Symbolize/Symbolize.h

@@ -58,11 +58,13 @@ class LLVMSymbolizer {
     bool RelativeAddresses = false;
     bool UntagAddresses = false;
     bool UseDIA = false;
+    bool DisableGsym = false;
     std::string DefaultArch;
     std::vector<std::string> DsymHints;
     std::string FallbackDebugPath;
     std::string DWPName;
     std::vector<std::string> DebugFileDirectory;
+    std::vector<std::string> GsymFileDirectory;
     size_t MaxCacheSize =
         sizeof(size_t) == 4
             ? 512 * 1024 * 1024 /* 512 MiB */
@@ -177,6 +179,7 @@ class LLVMSymbolizer {
   ObjectFile *lookUpBuildIDObject(const std::string &Path,
                                   const ELFObjectFileBase *Obj,
                                   const std::string &ArchName);
+  std::string lookUpGsymFile(const std::string &Path);
 
   bool findDebugBinary(const std::string &OrigPath,
                        const std::string &DebuglinkName, uint32_t CRCHash,

llvm/lib/DebugInfo/GSYM/CMakeLists.txt

@@ -4,6 +4,7 @@ add_llvm_component_library(LLVMDebugInfoGSYM
   FileWriter.cpp
   FunctionInfo.cpp
   GsymCreator.cpp
+  GsymDIContext.cpp
   GsymReader.cpp
   InlineInfo.cpp
   LineTable.cpp

llvm/lib/DebugInfo/GSYM/GsymDIContext.cpp

@@ -0,0 +1,166 @@
+//===-- GsymDIContext.cpp ------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===/
+
+#include "llvm/DebugInfo/GSYM/GsymDIContext.h"
+
+#include "llvm/DebugInfo/GSYM/GsymReader.h"
+#include "llvm/Support/Path.h"
+
+using namespace llvm;
+using namespace llvm::gsym;
+
+GsymDIContext::GsymDIContext(std::unique_ptr<GsymReader> Reader)
+    : DIContext(CK_GSYM), Reader(std::move(Reader)) {}
+
+void GsymDIContext::dump(raw_ostream &OS, DIDumpOptions DumpOpts) {}
+
+static bool fillLineInfoFromLocation(const SourceLocation &Location,
+                                     DILineInfoSpecifier Specifier,
+                                     DILineInfo &LineInfo) {
+  // FIXME Demangle in case of DINameKind::ShortName
+  if (Specifier.FNKind != DINameKind::None) {
+    LineInfo.FunctionName = Location.Name.str();
+  }
+
+  switch (Specifier.FLIKind) {
+  case DILineInfoSpecifier::FileLineInfoKind::RelativeFilePath:
+    // We have no information to determine the relative path, so we fall back to
+    // returning the absolute path.
+  case DILineInfoSpecifier::FileLineInfoKind::RawValue:
+  case DILineInfoSpecifier::FileLineInfoKind::AbsoluteFilePath:
+    if (Location.Dir.empty()) {
+      if (Location.Base.empty())
+        LineInfo.FileName = DILineInfo::BadString;
+      else
+        LineInfo.FileName = Location.Base.str();
+    } else {
+      SmallString<128> Path(Location.Dir);
+      sys::path::append(Path, Location.Base);
+      LineInfo.FileName = static_cast<std::string>(Path);
+    }
+    break;
+
+  case DILineInfoSpecifier::FileLineInfoKind::BaseNameOnly:
+    LineInfo.FileName = Location.Base.str();
+    break;
+
+  default:
+    return false;
+  }
+  LineInfo.Line = Location.Line;
+
+  // We don't have information in GSYM to fill any of the Source, Column,
+  // StartFileName or StartLine attributes.
+
+  return true;
+}
+
+std::optional<DILineInfo>
+GsymDIContext::getLineInfoForAddress(object::SectionedAddress Address,
+                                     DILineInfoSpecifier Specifier) {
+  if (Address.SectionIndex != object::SectionedAddress::UndefSection)
+    return {};
+
+  auto ResultOrErr = Reader->lookup(Address.Address);
+
+  if (!ResultOrErr) {
+    consumeError(ResultOrErr.takeError());
+    return {};
+  }
+
+  const auto &Result = *ResultOrErr;
+
+  DILineInfo LineInfo;
+
+  if (Result.Locations.empty()) {
+    // No debug info for this, we just had a symbol from the symbol table.
+
+    // FIXME Demangle in case of DINameKind::ShortName
+    if (Specifier.FNKind != DINameKind::None)
+      LineInfo.FunctionName = Result.FuncName.str();
+  } else if (!fillLineInfoFromLocation(Result.Locations.front(), Specifier,
+                                       LineInfo))
+    return {};
+
+  LineInfo.StartAddress = Result.FuncRange.start();
+
+  return LineInfo;
+}
+
+std::optional<DILineInfo>
+GsymDIContext::getLineInfoForDataAddress(object::SectionedAddress Address) {
+  // We can't implement this, there's no such information in the GSYM file.
+
+  return {};
+}
+
+DILineInfoTable
+GsymDIContext::getLineInfoForAddressRange(object::SectionedAddress Address,
+                                          uint64_t Size,
+                                          DILineInfoSpecifier Specifier) {
+  if (Size == 0)
+    return DILineInfoTable();
+
+  if (Address.SectionIndex != llvm::object::SectionedAddress::UndefSection)
+    return DILineInfoTable();
+
+  if (auto FuncInfoOrErr = Reader->getFunctionInfo(Address.Address)) {
+    DILineInfoTable Table;
+    if (FuncInfoOrErr->OptLineTable) {
+      const gsym::LineTable &LT = *FuncInfoOrErr->OptLineTable;
+      const uint64_t StartAddr = Address.Address;
+      const uint64_t EndAddr = Address.Address + Size;
+      for (const auto &LineEntry : LT) {
+        if (StartAddr <= LineEntry.Addr && LineEntry.Addr < EndAddr) {
+          // Use LineEntry.Addr, LineEntry.File (which is a file index into the
+          // files tables from the GsymReader), and LineEntry.Line (source line
+          // number) to add stuff to the DILineInfoTable
+        }
+      }
+    }
+    return Table;
+  } else {
+    consumeError(FuncInfoOrErr.takeError());
+    return DILineInfoTable();
+  }
+}
+
+DIInliningInfo
+GsymDIContext::getInliningInfoForAddress(object::SectionedAddress Address,
+                                         DILineInfoSpecifier Specifier) {
+  auto ResultOrErr = Reader->lookup(Address.Address);
+
+  if (!ResultOrErr)
+    return {};
+
+  const auto &Result = *ResultOrErr;
+
+  DIInliningInfo InlineInfo;
+
+  for (const auto &Location : Result.Locations) {
+    DILineInfo LineInfo;
+
+    if (!fillLineInfoFromLocation(Location, Specifier, LineInfo))
+      return {};
+
+    // Hm, that's probably something that should only be filled in the first or
+    // last frame?
+    LineInfo.StartAddress = Result.FuncRange.start();
+
+    InlineInfo.addFrame(LineInfo);
+  }
+
+  return InlineInfo;
+}
+
+std::vector<DILocal>
+GsymDIContext::getLocalsForAddress(object::SectionedAddress Address) {
+  // We can't implement this, there's no such information in the GSYM file.
+
+  return {};
+}

llvm/lib/DebugInfo/Symbolize/CMakeLists.txt

@@ -10,6 +10,7 @@ add_llvm_component_library(LLVMSymbolize
 
   LINK_COMPONENTS
   DebugInfoDWARF
+  DebugInfoGSYM
   DebugInfoPDB
   DebugInfoBTF
   Object

llvm/lib/DebugInfo/Symbolize/Symbolize.cpp

@@ -15,6 +15,8 @@
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/DebugInfo/BTF/BTFContext.h"
 #include "llvm/DebugInfo/DWARF/DWARFContext.h"
+#include "llvm/DebugInfo/GSYM/GsymDIContext.h"
+#include "llvm/DebugInfo/GSYM/GsymReader.h"
 #include "llvm/DebugInfo/PDB/PDB.h"
 #include "llvm/DebugInfo/PDB/PDBContext.h"
 #include "llvm/DebugInfo/Symbolize/SymbolizableObjectFile.h"
@@ -498,6 +500,34 @@ bool LLVMSymbolizer::getOrFindDebugBinary(const ArrayRef<uint8_t> BuildID,
   return false;
 }
 
+std::string LLVMSymbolizer::lookUpGsymFile(const std::string &Path) {
+  if (Opts.DisableGsym)
+    return {};
+
+  auto CheckGsymFile = [](const llvm::StringRef &GsymPath) {
+    sys::fs::file_status Status;
+    std::error_code EC = llvm::sys::fs::status(GsymPath, Status);
+    return !EC && !llvm::sys::fs::is_directory(Status);
+  };
+
+  // First, look beside the binary file
+  if (const auto GsymPath = Path + ".gsym"; CheckGsymFile(GsymPath))
+    return GsymPath;
+
+  // Then, look in the directories specified by GsymFileDirectory
+
+  for (const auto &Directory : Opts.GsymFileDirectory) {
+    SmallString<16> GsymPath = llvm::StringRef{Directory};
+    llvm::sys::path::append(GsymPath,
+                            llvm::sys::path::filename(Path) + ".gsym");
+
+    if (CheckGsymFile(GsymPath))
+      return static_cast<std::string>(GsymPath);
+  }
+
+  return {};
+}
+
 Expected<LLVMSymbolizer::ObjectPair>
 LLVMSymbolizer::getOrCreateObjectPair(const std::string &Path,
                                       const std::string &ArchName) {
@@ -634,30 +664,48 @@ LLVMSymbolizer::getOrCreateModuleInfo(StringRef ModuleName) {
   std::unique_ptr<DIContext> Context;
   // If this is a COFF object containing PDB info and not containing DWARF
   // section, 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);
-    // Use DWARF if there're DWARF sections.
-    bool HasDwarf =
-        llvm::any_of(Objects.first->sections(), [](SectionRef Section) -> bool {
-          if (Expected<StringRef> SectionName = Section.getName())
-            return SectionName.get() == ".debug_info";
-          return false;
-        });
-    if (!EC && !HasDwarf && DebugInfo != nullptr && !PDBFileName.empty()) {
-      using namespace pdb;
-      std::unique_ptr<IPDBSession> Session;
-
-      PDB_ReaderType ReaderType =
-          Opts.UseDIA ? PDB_ReaderType::DIA : PDB_ReaderType::Native;
-      if (auto Err = loadDataForEXE(ReaderType, Objects.first->getFileName(),
-                                    Session)) {
-        Modules.emplace(ModuleName, std::unique_ptr<SymbolizableModule>());
-        // Return along the PDB filename to provide more context
-        return createFileError(PDBFileName, std::move(Err));
+  // Create a DIContext to symbolize as follows:
+  // - If there is a GSYM file, create a GsymDIContext.
+  // - Otherwise, if this is a COFF object containing PDB info, create a
+  // PDBContext.
+  // - Otherwise, create a DWARFContext.
+  const auto GsymFile = lookUpGsymFile(BinaryName.str());
+  if (!GsymFile.empty()) {
+    auto ReaderOrErr = gsym::GsymReader::openFile(GsymFile);
+
+    if (ReaderOrErr) {
+      std::unique_ptr<gsym::GsymReader> Reader =
+          std::make_unique<gsym::GsymReader>(std::move(*ReaderOrErr));
+
+      Context = std::make_unique<gsym::GsymDIContext>(std::move(Reader));
+    }
+  }
+  if (!Context) {
+    if (auto CoffObject = dyn_cast<COFFObjectFile>(Objects.first)) {
+      const codeview::DebugInfo *DebugInfo;
+      StringRef PDBFileName;
+      auto EC = CoffObject->getDebugPDBInfo(DebugInfo, PDBFileName);
+      // Use DWARF if there're DWARF sections.
+      bool HasDwarf = llvm::any_of(
+          Objects.first->sections(), [](SectionRef Section) -> bool {
+            if (Expected<StringRef> SectionName = Section.getName())
+              return SectionName.get() == ".debug_info";
+            return false;
+          });
+      if (!EC && !HasDwarf && DebugInfo != nullptr && !PDBFileName.empty()) {
+        using namespace pdb;
+        std::unique_ptr<IPDBSession> Session;
+
+        PDB_ReaderType ReaderType =
+            Opts.UseDIA ? PDB_ReaderType::DIA : PDB_ReaderType::Native;
+        if (auto Err = loadDataForEXE(ReaderType, Objects.first->getFileName(),
+                                      Session)) {
+          Modules.emplace(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)));
       }
-      Context.reset(new PDBContext(*CoffObject, std::move(Session)));
     }
   }
   if (!Context)