Find PLT entries for x86, x86_64, and AArch64.

This adds a new method to ELFObjectFileBase that returns the symbols and addresses of PLT entries.

This design was suggested by pcc and eugenis in https://reviews.llvm.org/D49383.

Differential Revision: https://reviews.llvm.org/D50203

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@340610 91177308-0d34-0410-b5e6-96231b3b80d8

Author: jgalenson

include/llvm/MC/MCInstrAnalysis.h

@@ -23,6 +23,7 @@
 namespace llvm {
 
 class MCRegisterInfo;
+class Triple;
 
 class MCInstrAnalysis {
 protected:
@@ -105,6 +106,13 @@ class MCInstrAnalysis {
   virtual bool
   evaluateBranch(const MCInst &Inst, uint64_t Addr, uint64_t Size,
                  uint64_t &Target) const;
+
+  /// Returns (PLT virtual address, GOT virtual address) pairs for PLT entries.
+  virtual std::vector<std::pair<uint64_t, uint64_t>>
+  findPltEntries(uint64_t PltSectionVA, ArrayRef<uint8_t> PltContents,
+                 uint64_t GotPltSectionVA, const Triple &TargetTriple) const {
+    return {};
+  }
 };
 
 } // end namespace llvm

include/llvm/Object/ELFObjectFile.h

@@ -86,6 +86,8 @@ class ELFObjectFileBase : public ObjectFile {
   void setARMSubArch(Triple &TheTriple) const override;
 
   virtual uint16_t getEType() const = 0;
+
+  std::vector<std::pair<DataRefImpl, uint64_t>> getPltAddresses() const;
 };
 
 class ELFSectionRef : public SectionRef {

lib/Object/ELFObjectFile.cpp

@@ -14,6 +14,7 @@
 #include "llvm/Object/ELFObjectFile.h"
 #include "llvm/ADT/Triple.h"
 #include "llvm/BinaryFormat/ELF.h"
+#include "llvm/MC/MCInstrAnalysis.h"
 #include "llvm/MC/SubtargetFeature.h"
 #include "llvm/Object/ELF.h"
 #include "llvm/Object/ELFTypes.h"
@@ -23,6 +24,7 @@
 #include "llvm/Support/Endian.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/MathExtras.h"
+#include "llvm/Support/TargetRegistry.h"
 #include <algorithm>
 #include <cstddef>
 #include <cstdint>
@@ -327,3 +329,66 @@ void ELFObjectFileBase::setARMSubArch(Triple &TheTriple) const {
 
   TheTriple.setArchName(Triple);
 }
+
+std::vector<std::pair<DataRefImpl, uint64_t>>
+ELFObjectFileBase::getPltAddresses() const {
+  std::string Err;
+  const auto Triple = makeTriple();
+  const auto *T = TargetRegistry::lookupTarget(Triple.str(), Err);
+  if (!T)
+    return {};
+  uint64_t JumpSlotReloc = 0;
+  switch (Triple.getArch()) {
+    case Triple::x86:
+      JumpSlotReloc = ELF::R_386_JUMP_SLOT;
+      break;
+    case Triple::x86_64:
+      JumpSlotReloc = ELF::R_X86_64_JUMP_SLOT;
+      break;
+    case Triple::aarch64:
+      JumpSlotReloc = ELF::R_AARCH64_JUMP_SLOT;
+      break;
+    default:
+      return {};
+  }
+  const auto *MIA = T->createMCInstrAnalysis(T->createMCInstrInfo());
+  if (!MIA)
+    return {};
+  Optional<SectionRef> Plt = None, RelaPlt = None, GotPlt = None;
+  for (const SectionRef &Section : sections()) {
+    StringRef Name;
+    if (Section.getName(Name))
+      continue;
+    if (Name == ".plt")
+      Plt = Section;
+    else if (Name == ".rela.plt" || Name == ".rel.plt")
+      RelaPlt = Section;
+    else if (Name == ".got.plt")
+      GotPlt = Section;
+  }
+  if (!Plt || !RelaPlt || !GotPlt)
+    return {};
+  StringRef PltContents;
+  if (Plt->getContents(PltContents))
+    return {};
+  ArrayRef<uint8_t> PltBytes((const uint8_t *)PltContents.data(),
+                             Plt->getSize());
+  auto PltEntries = MIA->findPltEntries(Plt->getAddress(), PltBytes,
+                                        GotPlt->getAddress(), Triple);
+  // Build a map from GOT entry virtual address to PLT entry virtual address.
+  DenseMap<uint64_t, uint64_t> GotToPlt;
+  for (const auto &Entry : PltEntries)
+    GotToPlt.insert(std::make_pair(Entry.second, Entry.first));
+  // Find the relocations in the dynamic relocation table that point to
+  // locations in the GOT for which we know the corresponding PLT entry.
+  std::vector<std::pair<DataRefImpl, uint64_t>> Result;
+  for (const auto &Relocation : RelaPlt->relocations()) {
+    if (Relocation.getType() != JumpSlotReloc)
+      continue;
+    auto PltEntryIter = GotToPlt.find(Relocation.getOffset());
+    if (PltEntryIter != GotToPlt.end())
+      Result.push_back(std::make_pair(
+          Relocation.getSymbol()->getRawDataRefImpl(), PltEntryIter->second));
+  }
+  return Result;
+}

lib/Target/AArch64/MCTargetDesc/AArch64MCTargetDesc.cpp

@@ -24,6 +24,7 @@
 #include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/MC/MCStreamer.h"
 #include "llvm/MC/MCSubtargetInfo.h"
+#include "llvm/Support/Endian.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/TargetRegistry.h"
 
@@ -153,6 +154,31 @@ class AArch64MCInstrAnalysis : public MCInstrAnalysis {
     }
     return false;
   }
+
+  std::vector<std::pair<uint64_t, uint64_t>>
+  findPltEntries(uint64_t PltSectionVA, ArrayRef<uint8_t> PltContents,
+                 uint64_t GotPltSectionVA,
+                 const Triple &TargetTriple) const override {
+    // Do a lightweight parsing of PLT entries.
+    std::vector<std::pair<uint64_t, uint64_t>> Result;
+    for (uint64_t Byte = 0, End = PltContents.size(); Byte + 7 < End;
+         Byte += 4) {
+      uint32_t Insn = support::endian::read32le(PltContents.data() + Byte);
+      // Check for adrp.
+      if ((Insn & 0x9f000000) != 0x90000000)
+        continue;
+      uint64_t Imm = (((PltSectionVA + Byte) >> 12) << 12) +
+            (((Insn >> 29) & 3) << 12) + (((Insn >> 5) & 0x3ffff) << 14);
+      uint32_t Insn2 = support::endian::read32le(PltContents.data() + Byte + 4);
+      // Check for: ldr Xt, [Xn, #pimm].
+      if (Insn2 >> 22 == 0x3e5) {
+        Imm += ((Insn2 >> 10) & 0xfff) << 3;
+        Result.push_back(std::make_pair(PltSectionVA + Byte, Imm));
+        Byte += 4;
+      }
+    }
+    return Result;
+  }
 };
 
 } // end anonymous namespace

lib/Target/X86/MCTargetDesc/X86MCTargetDesc.cpp

@@ -384,6 +384,9 @@ class X86MCInstrAnalysis : public MCInstrAnalysis {
                             const MCInst &Inst) const override;
   bool clearsSuperRegisters(const MCRegisterInfo &MRI, const MCInst &Inst,
                             APInt &Mask) const override;
+  std::vector<std::pair<uint64_t, uint64_t>>
+  findPltEntries(uint64_t PltSectionVA, ArrayRef<uint8_t> PltContents,
+                 uint64_t GotSectionVA, const Triple &TargetTriple) const;
 };
 
 bool X86MCInstrAnalysis::isDependencyBreaking(const MCSubtargetInfo &STI,
@@ -510,6 +513,64 @@ bool X86MCInstrAnalysis::clearsSuperRegisters(const MCRegisterInfo &MRI,
   return Mask.getBoolValue();
 }
 
+static std::vector<std::pair<uint64_t, uint64_t>>
+findX86PltEntries(uint64_t PltSectionVA, ArrayRef<uint8_t> PltContents,
+                  uint64_t GotPltSectionVA) {
+  // Do a lightweight parsing of PLT entries.
+  std::vector<std::pair<uint64_t, uint64_t>> Result;
+  for (uint64_t Byte = 0, End = PltContents.size(); Byte + 6 < End; ) {
+    // Recognize a jmp.
+    if (PltContents[Byte] == 0xff && PltContents[Byte + 1] == 0xa3) {
+      // The jmp instruction at the beginning of each PLT entry jumps to the
+      // address of the base of the .got.plt section plus the immediate.
+      uint32_t Imm = support::endian::read32le(PltContents.data() + Byte + 2);
+      Result.push_back(
+          std::make_pair(PltSectionVA + Byte, GotPltSectionVA + Imm));
+      Byte += 6;
+    } else if (PltContents[Byte] == 0xff && PltContents[Byte + 1] == 0x25) {
+      // The jmp instruction at the beginning of each PLT entry jumps to the
+      // immediate.
+      uint32_t Imm = support::endian::read32le(PltContents.data() + Byte + 2);
+      Result.push_back(std::make_pair(PltSectionVA + Byte, Imm));
+      Byte += 6;
+    } else
+      Byte++;
+  }
+  return Result;
+}
+
+static std::vector<std::pair<uint64_t, uint64_t>>
+findX86_64PltEntries(uint64_t PltSectionVA, ArrayRef<uint8_t> PltContents) {
+  // Do a lightweight parsing of PLT entries.
+  std::vector<std::pair<uint64_t, uint64_t>> Result;
+  for (uint64_t Byte = 0, End = PltContents.size(); Byte + 6 < End; ) {
+    // Recognize a jmp.
+    if (PltContents[Byte] == 0xff && PltContents[Byte + 1] == 0x25) {
+      // The jmp instruction at the beginning of each PLT entry jumps to the
+      // address of the next instruction plus the immediate.
+      uint32_t Imm = support::endian::read32le(PltContents.data() + Byte + 2);
+      Result.push_back(
+          std::make_pair(PltSectionVA + Byte, PltSectionVA + Byte + 6 + Imm));
+      Byte += 6;
+    } else
+      Byte++;
+  }
+  return Result;
+}
+
+std::vector<std::pair<uint64_t, uint64_t>> X86MCInstrAnalysis::findPltEntries(
+    uint64_t PltSectionVA, ArrayRef<uint8_t> PltContents,
+    uint64_t GotPltSectionVA, const Triple &TargetTriple) const {
+  switch (TargetTriple.getArch()) {
+    case Triple::x86:
+      return findX86PltEntries(PltSectionVA, PltContents, GotPltSectionVA);
+    case Triple::x86_64:
+      return findX86_64PltEntries(PltSectionVA, PltContents);
+    default:
+      return {};
+  }
+}
+
 } // end of namespace X86_MC
 
 } // end of namespace llvm