[ELF] - Reuse Decompressor class.

[grimar]

Summary

Intention of change is to get rid of code duplication.
Decompressor was introduced in D28105.

Change allows to get rid of few methods relative to decompression.

[ruiu]

LGTM. Nice!

[grimar]

• D28105 was landed recently, this patch was updated to match latest changes in Decompressor API. Had to introduce one mote fatal() helper.

Is it OK to land ?

ELF/Driver.cpp

 #include "SymbolTable.h"
 #include "Target.h"
 #include "Threads.h"
 #include "Writer.h"
 #include "lld/Config/Version.h"
 #include "lld/Driver/Driver.h"
 #include "llvm/ADT/StringExtras.h"
 #include "llvm/ADT/StringSwitch.h"
+#include "llvm/DebugInfo/DWARF/DWARFCompression.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/TargetSelect.h"
 #include "llvm/Support/raw_ostream.h"
 #include <cstdlib>
 #include <utility>
 
 using namespace llvm;
 using namespace llvm::ELF;
if (Config->ICF)
     doIcf<ELFT>();
 
   // MergeInputSection::splitIntoPieces needs to be called before
   // any call of MergeInputSection::getOffset. Do that.
   forEach(Symtab.Sections.begin(), Symtab.Sections.end(),
           [](InputSectionBase<ELFT> *S) {
             if (!S->Live)
               return;
-            if (S->isCompressed())
+            if (DWARFCompression::isCompressedELFSection(S->Flags, S->Name))
               S->uncompress();
             if (auto *MS = dyn_cast<MergeInputSection<ELFT>>(S))
               MS->splitIntoPieces();
           });
 
   // Write the result to the file.
   writeResult<ELFT>();
 }

ELF/InputSection.h

public:
   ObjectFile<ELFT> *getFile() const { return File; }
   llvm::object::ELFFile<ELFT> getObj() const { return File->getObj(); }
   uintX_t getOffset(const DefinedRegular<ELFT> &Sym) const;
   InputSectionBase *getLinkOrderDep() const;
   // Translate an offset in the input section to an offset in the output
   // section.
   uintX_t getOffset(uintX_t Offset) const;
 
-  // ELF supports ZLIB-compressed section.
-  // Returns true if the section is compressed.
-  bool isCompressed() const;
   void uncompress();
 
   // Returns a source location string. Used to construct an error message.
   std::string getLocation(uintX_t Offset);
 
   void relocate(uint8_t *Buf, uint8_t *BufEnd);
-
-private:
-  std::pair<ArrayRef<uint8_t>, uint64_t>
-  getElfCompressedData(ArrayRef<uint8_t> Data);
-
-  std::pair<ArrayRef<uint8_t>, uint64_t>
-  getRawCompressedData(ArrayRef<uint8_t> Data);
 };
 
 // SectionPiece represents a piece of splittable section contents.
 // We allocate a lot of these and binary search on them. This means that they
 // have to be as compact as possible, which is why we don't store the size (can
 // be found by looking at the next one) and put the hash in a side table.
 struct SectionPiece {
   SectionPiece(size_t Off, bool Live = false)

ELF/InputSection.cpp

 #include "InputFiles.h"
 #include "LinkerScript.h"
 #include "Memory.h"
 #include "OutputSections.h"
 #include "Relocations.h"
 #include "SyntheticSections.h"
 #include "Target.h"
 #include "Thunks.h"
+#include "llvm/DebugInfo/DWARF/DWARFCompression.h"
 #include "llvm/Support/Compression.h"
 #include "llvm/Support/Endian.h"
 #include <mutex>
 
 using namespace llvm;
 using namespace llvm::ELF;
 using namespace llvm::object;
 using namespace llvm::support;
case EHFrame:
     // identify the start of the output .eh_frame.
     return Offset;
   case Merge:
     return cast<MergeInputSection<ELFT>>(this)->getOffset(Offset);
   }
   llvm_unreachable("invalid section kind");
 }
 
-template <class ELFT> bool InputSectionBase<ELFT>::isCompressed() const {
-  return (Flags & SHF_COMPRESSED) || Name.startswith(".zdebug");
-}
-
-// Returns compressed data and its size when uncompressed.
-template <class ELFT>
-std::pair<ArrayRef<uint8_t>, uint64_t>
-InputSectionBase<ELFT>::getElfCompressedData(ArrayRef<uint8_t> Data) {
-  // Compressed section with Elf_Chdr is the ELF standard.
-  if (Data.size() < sizeof(Elf_Chdr))
-    fatal(toString(this) + ": corrupted compressed section");
-  auto *Hdr = reinterpret_cast<const Elf_Chdr *>(Data.data());
-  if (Hdr->ch_type != ELFCOMPRESS_ZLIB)
-    fatal(toString(this) + ": unsupported compression type");
-  return {Data.slice(sizeof(*Hdr)), Hdr->ch_size};
-}
-
-// Returns compressed data and its size when uncompressed.
-template <class ELFT>
-std::pair<ArrayRef<uint8_t>, uint64_t>
-InputSectionBase<ELFT>::getRawCompressedData(ArrayRef<uint8_t> Data) {
-  // Compressed sections without Elf_Chdr header contain this header
-  // instead. This is a GNU extension.
-  struct ZlibHeader {
-    char Magic[4]; // Should be "ZLIB"
-    char Size[8];  // Uncompressed size in big-endian
-  };
-
-  if (Data.size() < sizeof(ZlibHeader))
-    fatal(toString(this) + ": corrupted compressed section");
-  auto *Hdr = reinterpret_cast<const ZlibHeader *>(Data.data());
-  if (memcmp(Hdr->Magic, "ZLIB", 4))
-    fatal(toString(this) + ": broken ZLIB-compressed section");
-  return {Data.slice(sizeof(*Hdr)), read64be(Hdr->Size)};
-}
-
 // Uncompress section contents. Note that this function is called
 // from parallel_for_each, so it must be thread-safe.
 template <class ELFT> void InputSectionBase<ELFT>::uncompress() {
-  if (!zlib::isAvailable())
-    fatal(toString(this) +
-          ": build lld with zlib to enable compressed sections support");
-
-  // This section is compressed. Here we decompress it. Ideally, all
-  // compressed sections have SHF_COMPRESSED bit and their contents
-  // start with headers of Elf_Chdr type. However, sections whose
-  // names start with ".zdebug_" don't have the bit and contains a raw
-  // ZLIB-compressed data (which is a bad thing because section names
-  // shouldn't be significant in ELF.) We need to be able to read both.
-  ArrayRef<uint8_t> Buf; // Compressed data
-  size_t Size;           // Uncompressed size
-  if (Flags & SHF_COMPRESSED)
-    std::tie(Buf, Size) = getElfCompressedData(Data);
-  else
-    std::tie(Buf, Size) = getRawCompressedData(Data);
-
+  DWARFCompression Uncompressor(Name, toStringRef(Data),
+                                ELFT::TargetEndianness == llvm::support::little,
+                                ELFT::Is64Bits);
+  size_t Size = Uncompressor.UncompressedSize;
   // Uncompress Buf.
   char *OutputBuf;
   {
     static std::mutex Mu;
     std::lock_guard<std::mutex> Lock(Mu);
     OutputBuf = BAlloc.Allocate<char>(Size);
   }
-  if (zlib::uncompress(toStringRef(Buf), OutputBuf, Size) != zlib::StatusOK)
-    fatal(toString(this) + ": error while uncompressing section");
+  if (!Uncompressor.uncompress(OutputBuf, Size))
+    fatal(toString(this) + ": " + Uncompressor.getErrorMessage());
   Data = ArrayRef<uint8_t>((uint8_t *)OutputBuf, Size);
 }
 
 template <class ELFT>
 typename ELFT::uint
 InputSectionBase<ELFT>::getOffset(const DefinedRegular<ELFT> &Sym) const {
   return getOffset(Sym.Value);
 }