[llvm-objdump] Add -R option

[paulsemel]

Summary

This option prints dynamic relocation entries of the given file

[paulsemel]

This is absolutely not finished. I kind of works for ELF files (tho it prints every relocations, not only dynamic ones).
I don't know much about other binary file types, I will probably need to dig more on this (and maybe some help if possible).

[paulsemel]

include/llvm/Object/ELFObjectFile.h

795 ↗

(On Diff #148966)

I guess this assert was not here for no reason. But I didn't understand why we were forbidding this function for ELF files other than ET_REL.. Can someone explain me those lines ?

[paulsemel]

Added helper function to get dynamic relocation sections.

[paulsemel]

Fix TODO comment.

[paulsemel]

Added long option.

[echristo]

include/llvm/Object/ELFObjectFile.h

795 ↗

(On Diff #148966)

I think it's that it was looking for a relocatable file and perhaps needs additional checks for any kind of relocatable rather than just relocatable object files.

tools/llvm-objdump/llvm-objdump.cpp

441 ↗

(On Diff #149774)

Can you add some explanatory comments here, it's not necessarily obvious what "undef" means in this context as it can be an overloaded term.

[paulsemel]

Added explanatory comment for the undef variable.

[paulsemel]

Thanks for reviewing :)

include/llvm/Object/ELFObjectFile.h

795 ↗

(On Diff #148966)

Yes, there is probably more check needed. At least, at the ELF format file level, there is no difference between ELF file types

tools/llvm-objdump/llvm-objdump.cpp

441 ↗

(On Diff #149774)

Sure !

[echristo]

Some of the logic in the function feels awkward, but that's a cleanup for another time probably.

-eric

[paulsemel]

In D47493#1124195, @echristo wrote:

Some of the logic in the function feels awkward, but that's a cleanup for another time probably.

-eric

Yes, I didn't really know how to do it better. I truly think that we want to output the sections and not directly the relocations.
This is why there is this weird logic (there is no pointer to reloc section in the Dynamic Section).
If you find any better way to do it, this might be awesome !
Will land tomorrow :)

llvm/trunk/include/llvm/Object/ELFObjectFile.h

 // This file declares the ELFObjectFile template class.
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef LLVM_OBJECT_ELFOBJECTFILE_H
 #define LLVM_OBJECT_ELFOBJECTFILE_H
 
 #include "llvm/ADT/ArrayRef.h"
+#include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/Triple.h"
 #include "llvm/ADT/iterator_range.h"
 #include "llvm/BinaryFormat/ELF.h"
 #include "llvm/MC/SubtargetFeature.h"
 #include "llvm/Object/Binary.h"
 #include "llvm/Object/ELF.h"
public:
 
   SubtargetFeatures getMIPSFeatures() const;
 
   SubtargetFeatures getARMFeatures() const;
 
   SubtargetFeatures getRISCVFeatures() const;
 
   void setARMSubArch(Triple &TheTriple) const override;
+
+  virtual uint16_t getEType() const = 0;
 };
 
 class ELFSectionRef : public SectionRef {
 public:
   ELFSectionRef(const SectionRef &B) : SectionRef(B) {
     assert(isa<ELFObjectFileBase>(SectionRef::getObject()));
   }
 

 
 inline ELFObjectFileBase::elf_symbol_iterator_range
 ELFObjectFileBase::symbols() const {
   return elf_symbol_iterator_range(symbol_begin(), symbol_end());
 }
 
 template <class ELFT> class ELFObjectFile : public ELFObjectFileBase {
   uint16_t getEMachine() const override;
+  uint16_t getEType() const override;
   uint64_t getSymbolSize(DataRefImpl Sym) const override;
 
 public:
   LLVM_ELF_IMPORT_TYPES_ELFT(ELFT)
 
   using uintX_t = typename ELFT::uint;
 
   using Elf_Sym = typename ELFT::Sym;
protected:
   uint64_t getSectionAlignment(DataRefImpl Sec) const override;
   bool isSectionCompressed(DataRefImpl Sec) const override;
   bool isSectionText(DataRefImpl Sec) const override;
   bool isSectionData(DataRefImpl Sec) const override;
   bool isSectionBSS(DataRefImpl Sec) const override;
   bool isSectionVirtual(DataRefImpl Sec) const override;
   relocation_iterator section_rel_begin(DataRefImpl Sec) const override;
   relocation_iterator section_rel_end(DataRefImpl Sec) const override;
+  std::vector<SectionRef> dynamic_relocation_sections() const override;
   section_iterator getRelocatedSection(DataRefImpl Sec) const override;
 
   void moveRelocationNext(DataRefImpl &Rel) const override;
   uint64_t getRelocationOffset(DataRefImpl Rel) const override;
   symbol_iterator getRelocationSymbol(DataRefImpl Rel) const override;
   uint64_t getRelocationType(DataRefImpl Rel) const override;
   void getRelocationTypeName(DataRefImpl Rel,
                              SmallVectorImpl<char> &Result) const override;
uint32_t ELFObjectFile<ELFT>::getSymbolAlignment(DataRefImpl Symb) const {
   return 0;
 }
 
 template <class ELFT>
 uint16_t ELFObjectFile<ELFT>::getEMachine() const {
   return EF.getHeader()->e_machine;
 }
 
+template <class ELFT> uint16_t ELFObjectFile<ELFT>::getEType() const {
+  return EF.getHeader()->e_type;
+}
+
 template <class ELFT>
 uint64_t ELFObjectFile<ELFT>::getSymbolSize(DataRefImpl Sym) const {
   return getSymbol(Sym)->st_size;
 }
 
 template <class ELFT>
 uint64_t ELFObjectFile<ELFT>::getCommonSymbolSizeImpl(DataRefImpl Symb) const {
   return getSymbol(Symb)->st_size;

 template <class ELFT>
 bool ELFObjectFile<ELFT>::isSectionBSS(DataRefImpl Sec) const {
   const Elf_Shdr *EShdr = getSection(Sec);
   return EShdr->sh_flags & (ELF::SHF_ALLOC | ELF::SHF_WRITE) &&
          EShdr->sh_type == ELF::SHT_NOBITS;
 }
 
 template <class ELFT>
+std::vector<SectionRef>
+ELFObjectFile<ELFT>::dynamic_relocation_sections() const {
+  std::vector<SectionRef> Res;
+  std::vector<uintptr_t> Offsets;
+
+  auto SectionsOrErr = EF.sections();
+  if (!SectionsOrErr)
+    return Res;
+
+  for (const Elf_Shdr &Sec : *SectionsOrErr) {
+    if (Sec.sh_type != ELF::SHT_DYNAMIC)
+      continue;
+    Elf_Dyn *Dynamic =
+        reinterpret_cast<Elf_Dyn *>((uintptr_t)base() + Sec.sh_offset);
+    for (; Dynamic->d_tag != ELF::DT_NULL; Dynamic++) {
+      if (Dynamic->d_tag == ELF::DT_REL || Dynamic->d_tag == ELF::DT_RELA ||
+          Dynamic->d_tag == ELF::DT_JMPREL) {
+        Offsets.push_back(Dynamic->d_un.d_val);
+      }
+    }
+  }
+  for (const Elf_Shdr &Sec : *SectionsOrErr) {
+    if (is_contained(Offsets, Sec.sh_offset))
+      Res.emplace_back(toDRI(&Sec), this);
+  }
+  return Res;
+}
+
+template <class ELFT>
 bool ELFObjectFile<ELFT>::isSectionVirtual(DataRefImpl Sec) const {
   return getSection(Sec)->sh_type == ELF::SHT_NOBITS;
 }
 
 template <class ELFT>
 relocation_iterator
 ELFObjectFile<ELFT>::section_rel_begin(DataRefImpl Sec) const {
   DataRefImpl RelData;
ELFObjectFile<ELFT>::getRelocationSymbol(DataRefImpl Rel) const {
   DataRefImpl SymbolData;
   SymbolData.d.a = sec->sh_link;
   SymbolData.d.b = symbolIdx;
   return symbol_iterator(SymbolRef(SymbolData, this));
 }
 
 template <class ELFT>
 uint64_t ELFObjectFile<ELFT>::getRelocationOffset(DataRefImpl Rel) const {
-  assert(EF.getHeader()->e_type == ELF::ET_REL &&
-         "Only relocatable object files have relocation offsets");
   const Elf_Shdr *sec = getRelSection(Rel);
   if (sec->sh_type == ELF::SHT_REL)
     return getRel(Rel)->r_offset;
 
   return getRela(Rel)->r_offset;
 }
 
 template <class ELFT>

llvm/trunk/include/llvm/Object/ObjectFile.h

public:
   ObjectFile() = delete;
   ObjectFile(const ObjectFile &other) = delete;
 
   uint64_t getCommonSymbolSize(DataRefImpl Symb) const {
     assert(getSymbolFlags(Symb) & SymbolRef::SF_Common);
     return getCommonSymbolSizeImpl(Symb);
   }
 
+  virtual std::vector<SectionRef> dynamic_relocation_sections() const {
+    return std::vector<SectionRef>();
+  }
+
   using symbol_iterator_range = iterator_range<symbol_iterator>;
   symbol_iterator_range symbols() const {
     return symbol_iterator_range(symbol_begin(), symbol_end());
   }
 
   virtual section_iterator section_begin() const = 0;
   virtual section_iterator section_end() const = 0;
 

llvm/trunk/tools/llvm-objdump/llvm-objdump.h

 extern cl::opt<bool> LinkOptHints;
 extern cl::opt<bool> InfoPlist;
 extern cl::opt<bool> DylibsUsed;
 extern cl::opt<bool> DylibId;
 extern cl::opt<bool> ObjcMetaData;
 extern cl::opt<std::string> DisSymName;
 extern cl::opt<bool> NonVerbose;
 extern cl::opt<bool> Relocations;
+extern cl::opt<bool> DynamicRelocations;
 extern cl::opt<bool> SectionHeaders;
 extern cl::opt<bool> SectionContents;
 extern cl::opt<bool> SymbolTable;
 extern cl::opt<bool> UnwindInfo;
 extern cl::opt<bool> PrintImmHex;
 extern cl::opt<DIDumpType> DwarfDumpType;
 
 // Various helper functions.

 void printWasmFileHeader(const object::ObjectFile *o);
 void printExportsTrie(const object::ObjectFile *o);
 void printRebaseTable(object::ObjectFile *o);
 void printBindTable(object::ObjectFile *o);
 void printLazyBindTable(object::ObjectFile *o);
 void printWeakBindTable(object::ObjectFile *o);
 void printRawClangAST(const object::ObjectFile *o);
 void PrintRelocations(const object::ObjectFile *o);
+void PrintDynamicRelocations(const object::ObjectFile *o);
 void PrintSectionHeaders(const object::ObjectFile *o);
 void PrintSectionContents(const object::ObjectFile *o);
 void PrintSymbolTable(const object::ObjectFile *o, StringRef ArchiveName,
                       StringRef ArchitectureName = StringRef());
 LLVM_ATTRIBUTE_NORETURN void error(Twine Message);
 LLVM_ATTRIBUTE_NORETURN void report_error(StringRef File, Twine Message);
 LLVM_ATTRIBUTE_NORETURN void report_error(StringRef File, std::error_code EC);
 LLVM_ATTRIBUTE_NORETURN void report_error(StringRef File, llvm::Error E);

llvm/trunk/tools/llvm-objdump/llvm-objdump.cpp

DisassembleFunctions("df",
                      cl::CommaSeparated,
                      cl::desc("List of functions to disassemble"));
 static StringSet<> DisasmFuncsSet;
 
 cl::opt<bool>
 llvm::Relocations("r", cl::desc("Display the relocation entries in the file"));
 
 cl::opt<bool>
+llvm::DynamicRelocations("dynamic-reloc",
+  cl::desc("Display the dynamic relocation entries in the file"));
+static cl::alias
+DynamicRelocationsd("R", cl::desc("Alias for --dynamic-reloc"),
+             cl::aliasopt(DynamicRelocations));
+
+cl::opt<bool>
 llvm::SectionContents("s", cl::desc("Display the content of each section"));
 
 cl::opt<bool>
 llvm::SymbolTable("t", cl::desc("Display the symbol table"));
 
 cl::opt<bool>
 llvm::ExportsTrie("exports-trie", cl::desc("Display mach-o exported symbols"));
 
static std::error_code getRelocationValueString(const ELFObjectFile<ELFT> *Obj,
   auto StrTabSec = EF.getSection(SymTab->sh_link);
   if (!StrTabSec)
     return errorToErrorCode(StrTabSec.takeError());
   auto StrTabOrErr = EF.getStringTable(*StrTabSec);
   if (!StrTabOrErr)
     return errorToErrorCode(StrTabOrErr.takeError());
   StringRef StrTab = *StrTabOrErr;
   int64_t addend = 0;
+  // If there is no Symbol associated with the relocation, we set the undef
+  // boolean value to 'true'. This will prevent us from calling functions that
+  // requires the relocation to be associated with a symbol.
+  bool undef = false;
   switch (Sec->sh_type) {
   default:
     return object_error::parse_failed;
   case ELF::SHT_REL: {
     // TODO: Read implicit addend from section data.
     break;
   }
   case ELF::SHT_RELA: {
     const Elf_Rela *ERela = Obj->getRela(Rel);
     addend = ERela->r_addend;
+    undef = ERela->getSymbol(false) == 0;
     break;
   }
   }
+  StringRef Target;
+  if (!undef) {
     symbol_iterator SI = RelRef.getSymbol();
     const Elf_Sym *symb = Obj->getSymbol(SI->getRawDataRefImpl());
-  StringRef Target;
     if (symb->getType() == ELF::STT_SECTION) {
       Expected<section_iterator> SymSI = SI->getSection();
       if (!SymSI)
         return errorToErrorCode(SymSI.takeError());
       const Elf_Shdr *SymSec = Obj->getSection((*SymSI)->getRawDataRefImpl());
       auto SecName = EF.getSectionName(SymSec);
       if (!SecName)
         return errorToErrorCode(SecName.takeError());
       Target = *SecName;
     } else {
       Expected<StringRef> SymName = symb->getName(StrTab);
       if (!SymName)
         return errorToErrorCode(SymName.takeError());
       Target = *SymName;
     }
+  } else
+    Target = "*ABS*";
 
   // Default scheme is to print Target, as well as "+ <addend>" for nonzero
   // addend. Should be acceptable for all normal purposes.
   std::string fmtbuf;
   raw_string_ostream fmt(fmtbuf);
   fmt << Target;
   if (addend != 0)
     fmt << (addend < 0 ? "" : "+") << addend;
for (const RelocationRef &Reloc : Section.relocations()) {
       error(getRelocationValueString(Reloc, valuestr));
       outs() << format(Fmt.data(), address) << " " << relocname << " "
              << valuestr << "\n";
     }
     outs() << "\n";
   }
 }
 
+void llvm::PrintDynamicRelocations(const ObjectFile *Obj) {
+
+  // For the moment, this option is for ELF only
+  if (!Obj->isELF())
+    return;
+
+  const auto *Elf = dyn_cast<ELFObjectFileBase>(Obj);
+
+  if (!Elf || Elf->getEType() != ELF::ET_DYN) {
+    error("not a dynamic object");
+    return;
+  }
+
+  StringRef Fmt = Obj->getBytesInAddress() > 4 ? "%016" PRIx64 : "%08" PRIx64;
+
+  std::vector<SectionRef> DynRelSec = Obj->dynamic_relocation_sections();
+  if (DynRelSec.empty())
+    return;
+
+  outs() << "DYNAMIC RELOCATION RECORDS\n";
+  for (const SectionRef &Section : DynRelSec) {
+    if (Section.relocation_begin() == Section.relocation_end())
+      continue;
+    for (const RelocationRef &Reloc : Section.relocations()) {
+      uint64_t address = Reloc.getOffset();
+      SmallString<32> relocname;
+      SmallString<32> valuestr;
+      Reloc.getTypeName(relocname);
+      error(getRelocationValueString(Reloc, valuestr));
+      outs() << format(Fmt.data(), address) << " " << relocname << " "
+             << valuestr << "\n";
+    }
+  }
+}
+
 void llvm::PrintSectionHeaders(const ObjectFile *Obj) {
   outs() << "Sections:\n"
             "Idx Name          Size      Address          Type\n";
   unsigned i = 0;
   for (const SectionRef &Section : ToolSectionFilter(*Obj)) {
     StringRef Name;
     error(Section.getName(Name));
     uint64_t Address = Section.getAddress();
else
       outs() << o->getFileName();
     outs() << ":\tfile format " << o->getFileFormatName() << "\n\n";
   }
 
   if (Disassemble)
     DisassembleObject(o, Relocations);
   if (Relocations && !Disassemble)
     PrintRelocations(o);
+  if (DynamicRelocations)
+    PrintDynamicRelocations(o);
   if (SectionHeaders)
     PrintSectionHeaders(o);
   if (SectionContents)
     PrintSectionContents(o);
   if (SymbolTable)
     PrintSymbolTable(o, ArchiveName);
   if (UnwindInfo)
     PrintUnwindInfo(o);
int main(int argc, char **argv) {
   // Defaults to a.out if no filenames specified.
   if (InputFilenames.size() == 0)
     InputFilenames.push_back("a.out");
 
   if (DisassembleAll || PrintSource || PrintLines)
     Disassemble = true;
   if (!Disassemble
       && !Relocations
+      && !DynamicRelocations
       && !SectionHeaders
       && !SectionContents
       && !SymbolTable
       && !UnwindInfo
       && !PrivateHeaders
       && !FirstPrivateHeader
       && !ExportsTrie
       && !Rebase