Use ELF dynamic symbols for disassembly

[samparker]

Summary

Disassembly currently begins from addresses obtained from the objects symbol table. For ELF, also add the dynamic symbols to the list so that we can more successfully disassemble stripped binaries.

[davidb]

Hi Sam,

In the case that an ELF binary has both a static and dynamic symbol table present the list of symbols will have redundant entries. Perhaps we should only add dynamic ELF symbols in the case that we have no static symbols?

[samparker]

Hi David,

Yes, good point, I will add a check.

Cheers,
sam

[samparker]

Now we only try to add dynamic symbols if there are no static symbols.

[samparker]

Reversed the conditional.

[samparker]

Just added diff context

llvm/trunk/test/tools/llvm-objdump/stripped-shared.test

+// This test checks that dynamic symbols are used when disassembling elf files.
+// RUN: llvm-objdump -d %p/Inputs/stripped-elf.so | FileCheck %s
+
+# CHECK: .init
+# CHECK: .plt
+# CHECK: .text
+# CHECK: func0
+# CHECK: func1
+# CHECK: func2
+# CHECK: .fini

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

 cl::opt<unsigned long long>
     StartAddress("start-address", cl::desc("Disassemble beginning at address"),
                  cl::value_desc("address"), cl::init(0));
 cl::opt<unsigned long long>
     StopAddress("stop-address", cl::desc("Stop disassembly at address"),
                 cl::value_desc("address"), cl::init(UINT64_MAX));
 static StringRef ToolName;
 
+typedef std::vector<std::tuple<uint64_t, StringRef, uint8_t>> SectionSymbolsTy;
+
 namespace {
 typedef std::function<bool(llvm::object::SectionRef const &)> FilterPredicate;
 
 class SectionFilterIterator {
 public:
   SectionFilterIterator(FilterPredicate P,
                         llvm::object::section_iterator const &I,
                         llvm::object::section_iterator const &E)
if (auto *Elf64LEObj = dyn_cast<ELF64LEObjectFile>(Obj))
     return Elf64LEObj->getSymbol(Sym.getRawDataRefImpl())->getType();
   if (auto *Elf32BEObj = dyn_cast<ELF32BEObjectFile>(Obj))
     return Elf32BEObj->getSymbol(Sym.getRawDataRefImpl())->getType();
   if (auto *Elf64BEObj = cast<ELF64BEObjectFile>(Obj))
     return Elf64BEObj->getSymbol(Sym.getRawDataRefImpl())->getType();
   llvm_unreachable("Unsupported binary format");
 }
 
+template <class ELFT> static void
+addDynamicElfSymbols(const ELFObjectFile<ELFT> *Obj,
+                     std::map<SectionRef, SectionSymbolsTy> &AllSymbols) {
+  for (auto Symbol : Obj->getDynamicSymbolIterators()) {
+    uint8_t SymbolType = Symbol.getELFType();
+    if (SymbolType != ELF::STT_FUNC || Symbol.getSize() == 0)
+      continue;
+
+    Expected<uint64_t> AddressOrErr = Symbol.getAddress();
+    if (!AddressOrErr)
+      report_error(Obj->getFileName(), AddressOrErr.takeError());
+    uint64_t Address = *AddressOrErr;
+
+    Expected<StringRef> Name = Symbol.getName();
+    if (!Name)
+      report_error(Obj->getFileName(), Name.takeError());
+    if (Name->empty())
+      continue;
+
+    Expected<section_iterator> SectionOrErr = Symbol.getSection();
+    if (!SectionOrErr)
+      report_error(Obj->getFileName(), SectionOrErr.takeError());
+    section_iterator SecI = *SectionOrErr;
+    if (SecI == Obj->section_end())
+      continue;
+
+    AllSymbols[*SecI].emplace_back(Address, *Name, SymbolType);
+  }
+}
+
+static void
+addDynamicElfSymbols(const ObjectFile *Obj,
+                     std::map<SectionRef, SectionSymbolsTy> &AllSymbols) {
+  assert(Obj->isELF());
+  if (auto *Elf32LEObj = dyn_cast<ELF32LEObjectFile>(Obj))
+    addDynamicElfSymbols(Elf32LEObj, AllSymbols);
+  else if (auto *Elf64LEObj = dyn_cast<ELF64LEObjectFile>(Obj))
+    addDynamicElfSymbols(Elf64LEObj, AllSymbols);
+  else if (auto *Elf32BEObj = dyn_cast<ELF32BEObjectFile>(Obj))
+    addDynamicElfSymbols(Elf32BEObj, AllSymbols);
+  else if (auto *Elf64BEObj = cast<ELF64BEObjectFile>(Obj))
+    addDynamicElfSymbols(Elf64BEObj, AllSymbols);
+  else
+    llvm_unreachable("Unsupported binary format");
+}
+
 static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) {
   if (StartAddress > StopAddress)
     error("Start address should be less than stop address");
 
   const Target *TheTarget = getTarget(Obj);
 
   // Package up features to be passed to target/subtarget
   SubtargetFeatures Features = Obj->getFeatures();
static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) {
   for (const SectionRef &Section : ToolSectionFilter(*Obj)) {
     section_iterator Sec2 = Section.getRelocatedSection();
     if (Sec2 != Obj->section_end())
       SectionRelocMap[*Sec2].push_back(Section);
   }
 
   // Create a mapping from virtual address to symbol name.  This is used to
   // pretty print the symbols while disassembling.
-  typedef std::vector<std::tuple<uint64_t, StringRef, uint8_t>> SectionSymbolsTy;
   std::map<SectionRef, SectionSymbolsTy> AllSymbols;
   for (const SymbolRef &Symbol : Obj->symbols()) {
     Expected<uint64_t> AddressOrErr = Symbol.getAddress();
     if (!AddressOrErr)
       report_error(Obj->getFileName(), AddressOrErr.takeError());
     uint64_t Address = *AddressOrErr;
 
     Expected<StringRef> Name = Symbol.getName();
for (const SymbolRef &Symbol : Obj->symbols()) {
 
     uint8_t SymbolType = ELF::STT_NOTYPE;
     if (Obj->isELF())
       SymbolType = getElfSymbolType(Obj, Symbol);
 
     AllSymbols[*SecI].emplace_back(Address, *Name, SymbolType);
 
   }
+  if (AllSymbols.empty() && Obj->isELF())
+    addDynamicElfSymbols(Obj, AllSymbols);
 
   // Create a mapping from virtual address to section.
   std::vector<std::pair<uint64_t, SectionRef>> SectionAddresses;
   for (SectionRef Sec : Obj->sections())
     SectionAddresses.emplace_back(Sec.getAddress(), Sec);
   array_pod_sort(SectionAddresses.begin(), SectionAddresses.end());
 
   // Linked executables (.exe and .dll files) typically don't include a real