Adding PIC support for ELF on x86_64 platforms

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@188726 91177308-0d34-0410-b5e6-96231b3b80d8

4 files changed, 244 insertions, 16 deletions

diff --git a/lib/ExecutionEngine/RuntimeDyld/RuntimeDyld.cpp b/lib/ExecutionEngine/RuntimeDyld/RuntimeDyld.cpp
index a00b951e0a..d36126a9e2 100644
--- a/lib/ExecutionEngine/RuntimeDyld/RuntimeDyld.cpp
+++ b/lib/ExecutionEngine/RuntimeDyld/RuntimeDyld.cpp
@@ -169,6 +169,9 @@ ObjectImage *RuntimeDyldImpl::loadObject(ObjectBuffer *InputBuffer) {
     }
   }
 
+  // Give the subclasses a chance to tie-up any loose ends.
+  finalizeLoad();
+
   return obj.take();
 }
 
@@ -424,6 +427,10 @@ uint8_t *RuntimeDyldImpl::createStubFunction(uint8_t *Addr) {
     writeInt16BE(Addr+6,  0x07F1);     // brc 15,%r1
     // 8-byte address stored at Addr + 8
     return Addr;
+  } else if (Arch == Triple::x86_64) {
+    *Addr      = 0xFF; // jmp
+    *(Addr+1)  = 0x25; // rip
+    // 32-bit PC-relative address of the GOT entry will be stored at Addr+2
   }
   return Addr;
 }
@@ -473,6 +480,7 @@ void RuntimeDyldImpl::resolveExternalSymbols() {
         // MemoryManager.
         uint8_t *Addr = (uint8_t*) MemMgr->getPointerToNamedFunction(Name.data(),
                                                                    true);
+        updateGOTEntries(Name, (uint64_t)Addr);
         DEBUG(dbgs() << "Resolving relocations Name: " << Name
                 << "\t" << format("%p", Addr)
                 << "\n");
diff --git a/lib/ExecutionEngine/RuntimeDyld/RuntimeDyldELF.cpp b/lib/ExecutionEngine/RuntimeDyld/RuntimeDyldELF.cpp
index 6ce4f672bf..6504f0e2d7 100644
--- a/lib/ExecutionEngine/RuntimeDyld/RuntimeDyldELF.cpp
+++ b/lib/ExecutionEngine/RuntimeDyld/RuntimeDyldELF.cpp
@@ -202,7 +202,8 @@ void RuntimeDyldELF::resolveX86_64Relocation(const SectionEntry &Section,
                                              uint64_t Offset,
                                              uint64_t Value,
                                              uint32_t Type,
-                                             int64_t Addend) {
+                                             int64_t  Addend,
+                                             uint64_t SymOffset) {
   switch (Type) {
   default:
     llvm_unreachable("Relocation type not implemented yet!");
@@ -227,6 +228,21 @@ void RuntimeDyldELF::resolveX86_64Relocation(const SectionEntry &Section,
                  << " at " << format("%p\n",Target));
     break;
   }
+  case ELF::R_X86_64_GOTPCREL: {
+    // findGOTEntry returns the 'G + GOT' part of the relocation calculation
+    // based on the load/target address of the GOT (not the current/local addr).
+    uint64_t GOTAddr = findGOTEntry(Value, SymOffset);
+    uint32_t *Target = reinterpret_cast<uint32_t*>(Section.Address + Offset);
+    uint64_t  FinalAddress = Section.LoadAddress + Offset;
+    // The processRelocationRef method combines the symbol offset and the addend
+    // and in most cases that's what we want.  For this relocation type, we need
+    // the raw addend, so we subtract the symbol offset to get it.
+    int64_t RealOffset = GOTAddr + Addend - SymOffset - FinalAddress;
+    assert(RealOffset <= INT32_MAX && RealOffset >= INT32_MIN);
+    int32_t TruncOffset = (RealOffset & 0xFFFFFFFF);
+    *Target = TruncOffset;
+    break;
+  }
   case ELF::R_X86_64_PC32: {
     // Get the placeholder value from the generated object since
     // a previous relocation attempt may have overwritten the loaded version
@@ -240,6 +256,16 @@ void RuntimeDyldELF::resolveX86_64Relocation(const SectionEntry &Section,
     *Target = TruncOffset;
     break;
   }
+  case ELF::R_X86_64_PC64: {
+    // Get the placeholder value from the generated object since
+    // a previous relocation attempt may have overwritten the loaded version
+    uint64_t *Placeholder = reinterpret_cast<uint64_t*>(Section.ObjAddress
+                                                                   + Offset);
+    uint64_t *Target = reinterpret_cast<uint64_t*>(Section.Address + Offset);
+    uint64_t  FinalAddress = Section.LoadAddress + Offset;
+    *Target = *Placeholder + Value + Addend - FinalAddress;
+    break;
+  }
   }
 }
 
@@ -584,7 +610,7 @@ void RuntimeDyldELF::findOPDEntrySection(ObjectImage &Obj,
       // Finally compares the Symbol value and the target symbol offset
       // to check if this .opd entry refers to the symbol the relocation
       // points to.
-      if (Rel.Addend != (intptr_t)TargetSymbolOffset)
+      if (Rel.Addend != (int64_t)TargetSymbolOffset)
         continue;
 
       section_iterator tsi(Obj.end_sections());
@@ -757,17 +783,19 @@ void RuntimeDyldELF::resolveSystemZRelocation(const SectionEntry &Section,
 void RuntimeDyldELF::resolveRelocation(const RelocationEntry &RE,
                                        uint64_t Value) {
   const SectionEntry &Section = Sections[RE.SectionID];
-  return resolveRelocation(Section, RE.Offset, Value, RE.RelType, RE.Addend);
+  return resolveRelocation(Section, RE.Offset, Value, RE.RelType, RE.Addend,
+                           RE.SymOffset);
 }
 
 void RuntimeDyldELF::resolveRelocation(const SectionEntry &Section,
                                        uint64_t Offset,
                                        uint64_t Value,
                                        uint32_t Type,
-                                       int64_t Addend) {
+                                       int64_t  Addend,
+                                       uint64_t SymOffset) {
   switch (Arch) {
   case Triple::x86_64:
-    resolveX86_64Relocation(Section, Offset, Value, Type, Addend);
+    resolveX86_64Relocation(Section, Offset, Value, Type, Addend, SymOffset);
     break;
   case Triple::x86:
     resolveX86Relocation(Section, Offset,
@@ -830,6 +858,7 @@ void RuntimeDyldELF::processRelocationRef(unsigned SectionID,
   }
   if (lsi != Symbols.end()) {
     Value.SectionID = lsi->second.first;
+    Value.Offset = lsi->second.second;
     Value.Addend = lsi->second.second + Addend;
   } else {
     // Search for the symbol in the global symbol table
@@ -838,6 +867,7 @@ void RuntimeDyldELF::processRelocationRef(unsigned SectionID,
       gsi = GlobalSymbolTable.find(TargetName.data());
     if (gsi != GlobalSymbolTable.end()) {
       Value.SectionID = gsi->second.first;
+      Value.Offset = gsi->second.second;
       Value.Addend = gsi->second.second + Addend;
     } else {
       switch (SymType) {
@@ -860,6 +890,7 @@ void RuntimeDyldELF::processRelocationRef(unsigned SectionID,
           Value.Addend = Addend;
           break;
         }
+        case SymbolRef::ST_Data:
         case SymbolRef::ST_Unknown: {
           Value.SymbolName = TargetName.data();
           Value.Addend = Addend;
@@ -1150,8 +1181,67 @@ void RuntimeDyldELF::processRelocationRef(unsigned SectionID,
                         ELF::R_390_PC32DBL, Addend);
     else
       resolveRelocation(Section, Offset, StubAddress, RelType, Addend);
+  } else if (Arch == Triple::x86_64 && RelType == ELF::R_X86_64_PLT32) {
+    // The way the PLT relocations normally work is that the linker allocates the
+    // PLT and this relocation makes a PC-relative call into the PLT.  The PLT
+    // entry will then jump to an address provided by the GOT.  On first call, the
+    // GOT address will point back into PLT code that resolves the symbol.  After
+    // the first call, the GOT entry points to the actual function.
+    //
+    // For local functions we're ignoring all of that here and just replacing
+    // the PLT32 relocation type with PC32, which will translate the relocation
+    // into a PC-relative call directly to the function. For external symbols we
+    // can't be sure the function will be within 2^32 bytes of the call site, so
+    // we need to create a stub, which calls into the GOT.  This case is
+    // equivalent to the usual PLT implementation except that we use the stub
+    // mechanism in RuntimeDyld (which puts stubs at the end of the section)
+    // rather than allocating a PLT section.
+    if (Value.SymbolName) {
+      // This is a call to an external function.
+      // Look for an existing stub.
+      SectionEntry &Section = Sections[SectionID];
+      StubMap::const_iterator i = Stubs.find(Value);
+      uintptr_t StubAddress;
+      if (i != Stubs.end()) {
+        StubAddress = uintptr_t(Section.Address) + i->second;
+        DEBUG(dbgs() << " Stub function found\n");
+      } else {
+        // Create a new stub function (equivalent to a PLT entry).
+        DEBUG(dbgs() << " Create a new stub function\n");
+
+        uintptr_t BaseAddress = uintptr_t(Section.Address);
+        uintptr_t StubAlignment = getStubAlignment();
+        StubAddress = (BaseAddress + Section.StubOffset +
+                      StubAlignment - 1) & -StubAlignment;
+        unsigned StubOffset = StubAddress - BaseAddress;
+        Stubs[Value] = StubOffset;
+        createStubFunction((uint8_t *)StubAddress);
+
+        // Create a GOT entry for the external function.
+        GOTEntries.push_back(Value);
+
+        // Make our stub function a relative call to the GOT entry.
+        RelocationEntry RE(SectionID, StubOffset + 2,
+                           ELF::R_X86_64_GOTPCREL, -4);
+        addRelocationForSymbol(RE, Value.SymbolName);
+
+        // Bump our stub offset counter
+        Section.StubOffset = StubOffset + getMaxStubSize();
+      }
+
+      // Make the target call a call into the stub table.
+      resolveRelocation(Section, Offset, StubAddress,
+                      ELF::R_X86_64_PC32, Addend);
+    } else {
+      RelocationEntry RE(SectionID, Offset, ELF::R_X86_64_PC32, Value.Addend,
+                         Value.Offset);
+      addRelocationForSection(RE, Value.SectionID);
+    }
   } else {
-    RelocationEntry RE(SectionID, Offset, RelType, Value.Addend);
+    if (Arch == Triple::x86_64 && RelType == ELF::R_X86_64_GOTPCREL) {
+      GOTEntries.push_back(Value);
+    }
+    RelocationEntry RE(SectionID, Offset, RelType, Value.Addend, Value.Offset);
     if (Value.SymbolName)
       addRelocationForSymbol(RE, Value.SymbolName);
     else
@@ -1159,6 +1249,106 @@ void RuntimeDyldELF::processRelocationRef(unsigned SectionID,
   }
 }
 
+void RuntimeDyldELF::updateGOTEntries(StringRef Name, uint64_t Addr) {
+  for (int i = 0, e = GOTEntries.size(); i != e; ++i) {
+    if (GOTEntries[i].SymbolName != 0 && GOTEntries[i].SymbolName == Name) {
+      GOTEntries[i].Offset = Addr;
+    }
+  }
+}
+
+size_t RuntimeDyldELF::getGOTEntrySize() {
+  // We don't use the GOT in all of these cases, but it's essentially free
+  // to put them all here.
+  size_t Result = 0;
+  switch (Arch) {
+  case Triple::x86_64:
+  case Triple::aarch64:
+  case Triple::ppc64:
+  case Triple::ppc64le:
+  case Triple::systemz:
+    Result = sizeof(uint64_t);
+    break;
+  case Triple::x86:
+  case Triple::arm:
+  case Triple::thumb:
+  case Triple::mips:
+  case Triple::mipsel:
+    Result = sizeof(uint32_t);
+    break;
+  default: llvm_unreachable("Unsupported CPU type!");
+  }
+  return Result;
+}
+
+uint64_t RuntimeDyldELF::findGOTEntry(uint64_t LoadAddress,
+                                      uint64_t Offset) {
+  assert(GOTSectionID != 0
+         && "Attempting to lookup GOT entry but the GOT was never allocated.");
+  if (GOTSectionID == 0) {
+    return 0;
+  }
+
+  size_t GOTEntrySize = getGOTEntrySize();
+
+  // Find the matching entry in our vector.
+  int GOTIndex = -1;
+  uint64_t SymbolOffset = 0;
+  for (int i = 0, e = GOTEntries.size(); i != e; ++i) {
+    if (GOTEntries[i].SymbolName == 0) {
+      if (getSectionLoadAddress(GOTEntries[i].SectionID) == LoadAddress &&
+          GOTEntries[i].Offset == Offset) {
+        GOTIndex = i;
+        SymbolOffset = GOTEntries[i].Offset;
+        break;
+      }
+    } else {
+      // GOT entries for external symbols use the addend as the address when
+      // the external symbol has been resolved.
+      if (GOTEntries[i].Offset == LoadAddress) {
+        GOTIndex = i;
+        // Don't use the Addend here.  The relocation handler will use it.
+        break;
+      }
+    }
+  }
+  assert(GOTIndex != -1 && "Unable to find requested GOT entry.");
+  if (GOTIndex == -1)
+    return 0;
+
+  if (GOTEntrySize == sizeof(uint64_t)) {
+    uint64_t *LocalGOTAddr = (uint64_t*)getSectionAddress(GOTSectionID);
+    // Fill in this entry with the address of the symbol being referenced.
+    LocalGOTAddr[GOTIndex] = LoadAddress + SymbolOffset;
+  } else {
+    uint32_t *LocalGOTAddr = (uint32_t*)getSectionAddress(GOTSectionID);
+    // Fill in this entry with the address of the symbol being referenced.
+    LocalGOTAddr[GOTIndex] = (uint32_t)(LoadAddress + SymbolOffset);
+  }
+
+  // Calculate the load address of this entry
+  return getSectionLoadAddress(GOTSectionID) + (GOTIndex * GOTEntrySize);
+}
+
+void RuntimeDyldELF::finalizeLoad() {
+  // Allocate the GOT if necessary
+  size_t numGOTEntries = GOTEntries.size();
+  if (numGOTEntries != 0) {
+    // Allocate memory for the section
+    unsigned SectionID = Sections.size();
+    size_t TotalSize = numGOTEntries * getGOTEntrySize();
+    uint8_t *Addr = MemMgr->allocateDataSection(TotalSize, getGOTEntrySize(),
+                                                SectionID, false);
+    if (!Addr)
+      report_fatal_error("Unable to allocate memory for GOT!");
+    Sections.push_back(SectionEntry(".got", Addr, TotalSize, 0));
+    // For now, initialize all GOT entries to zero.  We'll fill them in as
+    // needed when GOT-based relocations are applied.
+    memset(Addr, 0, TotalSize);
+    GOTSectionID = SectionID;
+  }
+}
+
 bool RuntimeDyldELF::isCompatibleFormat(const ObjectBuffer *Buffer) const {
   if (Buffer->getBufferSize() < strlen(ELF::ElfMagic))
     return false;
diff --git a/lib/ExecutionEngine/RuntimeDyld/RuntimeDyldELF.h b/lib/ExecutionEngine/RuntimeDyld/RuntimeDyldELF.h
index 794c7ece10..14fb5740e5 100644
--- a/lib/ExecutionEngine/RuntimeDyld/RuntimeDyldELF.h
+++ b/lib/ExecutionEngine/RuntimeDyld/RuntimeDyldELF.h
@@ -35,13 +35,15 @@ class RuntimeDyldELF : public RuntimeDyldImpl {
                          uint64_t Offset,
                          uint64_t Value,
                          uint32_t Type,
-                         int64_t Addend);
+                         int64_t Addend,
+                         uint64_t SymOffset=0);
 
   void resolveX86_64Relocation(const SectionEntry &Section,
                                uint64_t Offset,
                                uint64_t Value,
                                uint32_t Type,
-                               int64_t Addend);
+                               int64_t  Addend,
+                               uint64_t SymOffset);
 
   void resolveX86Relocation(const SectionEntry &Section,
                             uint64_t Offset,
@@ -84,8 +86,18 @@ class RuntimeDyldELF : public RuntimeDyldImpl {
                            ObjSectionToIDMap &LocalSections,
                            RelocationValueRef &Rel);
 
+  uint64_t findGOTEntry(uint64_t LoadAddr, uint64_t Offset);
+  size_t getGOTEntrySize();
+
+  virtual void updateGOTEntries(StringRef Name, uint64_t Addr);
+
+  SmallVector<RelocationValueRef, 2>  GOTEntries;
+  unsigned GOTSectionID;
+
 public:
-  RuntimeDyldELF(RTDyldMemoryManager *mm) : RuntimeDyldImpl(mm) {}
+  RuntimeDyldELF(RTDyldMemoryManager *mm) : RuntimeDyldImpl(mm),
+                                            GOTSectionID(0)
+                                          {}
 
   virtual void resolveRelocation(const RelocationEntry &RE, uint64_t Value);
   virtual void processRelocationRef(unsigned SectionID,
@@ -97,6 +109,7 @@ public:
   virtual bool isCompatibleFormat(const ObjectBuffer *Buffer) const;
   virtual ObjectImage *createObjectImage(ObjectBuffer *InputBuffer);
   virtual StringRef getEHFrameSection();
+  virtual void finalizeLoad();
   virtual ~RuntimeDyldELF();
 };
 
diff --git a/lib/ExecutionEngine/RuntimeDyld/RuntimeDyldImpl.h b/lib/ExecutionEngine/RuntimeDyld/RuntimeDyldImpl.h
index 14d945b5b7..77e25626d2 100644
--- a/lib/ExecutionEngine/RuntimeDyld/RuntimeDyldImpl.h
+++ b/lib/ExecutionEngine/RuntimeDyld/RuntimeDyldImpl.h
@@ -80,14 +80,18 @@ public:
   unsigned SectionID;
 
   /// Offset - offset into the section.
-  uintptr_t Offset;
+  uint64_t Offset;
 
   /// RelType - relocation type.
   uint32_t RelType;
 
   /// Addend - the relocation addend encoded in the instruction itself.  Also
   /// used to make a relocation section relative instead of symbol relative.
-  intptr_t Addend;
+  int64_t Addend;
+
+  /// SymOffset - Section offset of the relocation entry's symbol (used for GOT
+  /// lookup).
+  uint64_t SymOffset;
 
   /// True if this is a PCRel relocation (MachO specific).
   bool IsPCRel;
@@ -97,20 +101,26 @@ public:
 
   RelocationEntry(unsigned id, uint64_t offset, uint32_t type, int64_t addend)
     : SectionID(id), Offset(offset), RelType(type), Addend(addend),
-      IsPCRel(false), Size(0) {}
+      SymOffset(0), IsPCRel(false), Size(0) {}
+
+  RelocationEntry(unsigned id, uint64_t offset, uint32_t type, int64_t addend,
+                  uint64_t symoffset)
+    : SectionID(id), Offset(offset), RelType(type), Addend(addend),
+      SymOffset(symoffset), IsPCRel(false), Size(0) {}
 
   RelocationEntry(unsigned id, uint64_t offset, uint32_t type, int64_t addend,
                   bool IsPCRel, unsigned Size)
     : SectionID(id), Offset(offset), RelType(type), Addend(addend),
-      IsPCRel(IsPCRel), Size(Size) {}
+      SymOffset(0), IsPCRel(IsPCRel), Size(Size) {}
 };
 
 class RelocationValueRef {
 public:
   unsigned  SectionID;
-  intptr_t  Addend;
+  uint64_t  Offset;
+  int64_t   Addend;
   const char *SymbolName;
-  RelocationValueRef(): SectionID(0), Addend(0), SymbolName(0) {}
+  RelocationValueRef(): SectionID(0), Offset(0), Addend(0), SymbolName(0) {}
 
   inline bool operator==(const RelocationValueRef &Other) const {
     return std::memcmp(this, &Other, sizeof(RelocationValueRef)) == 0;
@@ -175,7 +185,7 @@ protected:
     else if (Arch == Triple::ppc64 || Arch == Triple::ppc64le)
       return 44;
     else if (Arch == Triple::x86_64)
-      return 8; // GOT
+      return 6; // 2-byte jmp instruction + 32-bit relative address
     else if (Arch == Triple::systemz)
       return 16;
     else
@@ -292,6 +302,11 @@ protected:
 
   /// \brief Resolve relocations to external symbols.
   void resolveExternalSymbols();
+
+  /// \brief Update GOT entries for external symbols.
+  // The base class does nothing.  ELF overrides this.
+  virtual void updateGOTEntries(StringRef Name, uint64_t Addr) {}
+
   virtual ObjectImage *createObjectImage(ObjectBuffer *InputBuffer);
 public:
   RuntimeDyldImpl(RTDyldMemoryManager *mm) : MemMgr(mm), HasError(false) {}
@@ -336,6 +351,8 @@ public:
   virtual bool isCompatibleFormat(const ObjectBuffer *Buffer) const = 0;
 
   virtual StringRef getEHFrameSection();
+
+  virtual void finalizeLoad() {}
 };
 
 } // end namespace llvm