Reland "[LLVM][llvm-objcopy] Added basic plumbing to get things started"

As discussed on llvm-dev I've implemented the first basic steps towards
llvm-objcopy/llvm-objtool (name pending).

This change adds the ability to copy (without modification) 64-bit
little endian ELF executables that have SHT_PROGBITS, SHT_NOBITS,
SHT_NULL and SHT_STRTAB sections.

Patch by Jake Ehrlich

Differential Revision: https://reviews.llvm.org/D33964

llvm-svn: 309643

llvm/test/CMakeLists.txt

@@ -61,6 +61,7 @@ set(LLVM_TEST_DEPENDS
           llvm-modextract
           llvm-mt
           llvm-nm
+          llvm-objcopy
           llvm-objdump
           llvm-opt-report
           llvm-pdbutil

llvm/test/lit.cfg

@@ -302,6 +302,7 @@ for pattern in [r"\bbugpoint\b(?!-)",
                 r"\bllvm-mcmarkup\b",
                 r"\bllvm-modextract\b",
                 r"\bllvm-nm\b",
+                r"\bllvm-objcopy\b",
                 r"\bllvm-objdump\b",
                 r"\bllvm-pdbutil\b",
                 r"\bllvm-profdata\b",

llvm/test/tools/llvm-objcopy/basic-copy.test

@@ -0,0 +1,47 @@
+# RUN: yaml2obj %s > %t
+# RUN: llvm-objcopy %t %t2
+# RUN: llvm-readobj -sections %t2 | FileCheck %s
+
+!ELF
+FileHeader:
+  Class:           ELFCLASS64
+  Data:            ELFDATA2LSB
+  Type:            ET_EXEC
+  Machine:         EM_X86_64
+Sections:
+  - Name:            .bss
+    Type:            SHT_NOBITS
+    Flags:           [ SHF_ALLOC ]
+    AddressAlign:    0x0000000000000010
+    Size:            64
+  - Name:            .text
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC, SHF_EXECINSTR ]
+    AddressAlign:    0x0000000000000010
+    Content:         "00000000"
+
+# CHECK: Type: SHT_NULL
+
+# CHECK:      Name: .bss
+# CHECK-NEXT: Type: SHT_NOBITS
+# CHECK-NEXT: Flags [
+# CHECK-NEXT:   SHF_ALLOC
+# CHECK-NEXT: ]
+# CHECK-NEXT: Address:
+# CHECK-NEXT: Offset: [[OFFSET:0x[0-9A-F]+]]
+# CHECK-NEXT: Size: 64
+
+# CHECK:      Name: .text
+# CHECK-NEXT: Type: SHT_PROGBITS
+# CHECK-NEXT: Flags [
+# CHECK-NEXT:   SHF_ALLOC
+# CHECK-NEXT:   SHF_EXECINSTR
+# CHECK-NEXT: ]
+# CHECK-NEXT: Address:
+# CHECK-NEXT: Offset: [[OFFSET]]
+# CHECK-NEXT: Size: 4
+
+# CHECK:      Name: .shstrtab
+# CHECK-NEXT: Type: SHT_STRTAB
+# CHECK-NEXT: Flags [
+# CHECK-NEXT: ]

llvm/test/tools/llvm-objcopy/empty-section.test

@@ -0,0 +1,55 @@
+# RUN: yaml2obj %s > %t
+# RUN: llvm-objcopy %t %t2
+# RUN: llvm-readobj -sections %t2 | FileCheck %s
+
+!ELF
+FileHeader:
+  Class:           ELFCLASS64
+  Data:            ELFDATA2LSB
+  Type:            ET_EXEC
+  Machine:         EM_X86_64
+Sections:
+  - Name:            .text
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC, SHF_EXECINSTR ]
+    Address:         0x0
+    AddressAlign:    0x0000000000001000
+    Content:         "00000000"
+  - Name:            .empty
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC ]
+    Address:         0x1000
+    AddressAlign:    0x0000000000001000
+    Content:         ""
+  - Name:            .data
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC ]
+    Address:         0x1000
+    AddressAlign:    0x0000000000001000
+    Content:         "00000000"
+
+
+# CHECK:      Name: .text
+# CHECK-NEXT: Type: SHT_PROGBITS
+# CHECK-NEXT: Flags [
+# CHECK-NEXT:   SHF_ALLOC
+# CHECK-NEXT:   SHF_EXECINSTR
+# CHECK-NEXT: ]
+
+# CHECK:      Name: .empty
+# CHECK-NEXT: Type: SHT_PROGBITS
+# CHECK-NEXT: Flags [
+# CHECK-NEXT:   SHF_ALLOC
+# CHECK-NEXT: ]
+# CHECK-NEXT: Address: 0x1000
+# CHECK-NEXT: Offset: 0x2000
+# CHECK-NEXT: Size: 0
+
+# CHECK:      Name: .data
+# CHECK-NEXT: Type: SHT_PROGBITS
+# CHECK-NEXT: Flags [
+# CHECK-NEXT:   SHF_ALLOC
+# CHECK-NEXT: ]
+# CHECK-NEXT: Address: 0x1000
+# CHECK-NEXT: Offset: 0x2000
+# CHECK-NEXT: Size: 4

llvm/test/tools/llvm-objcopy/program-headers.test

@@ -0,0 +1,71 @@
+# RUN: yaml2obj %s -o %t
+# RUN: llvm-objcopy %t %t2
+# RUN: llvm-readobj -program-headers %t2 | FileCheck %s
+
+!ELF
+FileHeader:
+  Class:           ELFCLASS64
+  Data:            ELFDATA2LSB
+  Type:            ET_EXEC
+  Machine:         EM_X86_64
+Sections:
+  - Name:            .text
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC, SHF_EXECINSTR ]
+    Address:         0xAAAA1000
+    AddressAlign:    0x0000000000001000
+    Content:         "00000000"
+  - Name:            .init
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC, SHF_EXECINSTR ]
+    Content:         "00000000"
+    Address:         0xAAAA1010
+    AddressAlign:    0x0000000000000010
+  - Name:            .data
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC ]
+    Content:         "00000000"
+    Address:         0xAAAA2000
+    AddressAlign:    0x0000000000001000
+ProgramHeaders:
+  - Type: PT_LOAD
+    Flags: [ PF_X, PF_R ]
+    VAddr: 0xAAAA1000
+    PAddr: 0xFFFF1000
+    Sections:
+      - Section: .text
+      - Section: .init
+  - Type: PT_LOAD
+    Flags: [ PF_R ]
+    VAddr: 0xAAAA2000
+    PAddr: 0xFFFF2000
+    Sections:
+      - Section: .data
+
+#CHECK:     ProgramHeaders [
+#CHECK-NEXT:   ProgramHeader {
+#CHECK-NEXT:    Type: PT_LOAD
+#CHECK-NEXT:    Offset: 0x1000
+#CHECK-NEXT:    VirtualAddress: 0xAAAA1000
+#CHECK-NEXT:    PhysicalAddress: 0xFFFF1000
+#CHECK-NEXT:    FileSize: 20
+#CHECK-NEXT:    MemSize: 20
+#CHECK-NEXT:    Flags [
+#CHECK-NEXT:      PF_R
+#CHECK-NEXT:      PF_X
+#CHECK-NEXT:    ]
+#CHECK-NEXT:    Alignment: 4096
+#CHECK-NEXT:  }
+#CHECK-NEXT:  ProgramHeader {
+#CHECK-NEXT:    Type: PT_LOAD
+#CHECK-NEXT:    Offset: 0x2000
+#CHECK-NEXT:    VirtualAddress: 0xAAAA2000
+#CHECK-NEXT:    PhysicalAddress: 0xFFFF2000
+#CHECK-NEXT:    FileSize: 4
+#CHECK-NEXT:    MemSize: 4
+#CHECK-NEXT:    Flags [
+#CHECK-NEXT:      PF_R
+#CHECK-NEXT:    ]
+#CHECK-NEXT:    Alignment: 4096
+#CHECK-NEXT:  }
+#CHECK-NEXT:]

llvm/tools/LLVMBuild.txt

@@ -40,6 +40,7 @@ subdirectories =
  llvm-modextract
  llvm-mt
  llvm-nm
+ llvm-objcopy
  llvm-objdump
  llvm-pdbutil
  llvm-profdata

llvm/tools/llvm-objcopy/CMakeLists.txt

@@ -0,0 +1,9 @@
+set(LLVM_LINK_COMPONENTS
+  Object
+  Support
+  MC
+  )
+add_llvm_tool(llvm-objcopy
+  llvm-objcopy.cpp
+  Object.cpp
+  )

llvm/tools/llvm-objcopy/LLVMBuild.txt

@@ -0,0 +1,21 @@
+;===- ./tools/llvm-objcopy/LLVMBuild.txt -----------------------*- Conf -*--===;
+;
+;                     The LLVM Compiler Infrastructure
+;
+; This file is distributed under the University of Illinois Open Source
+; License. See LICENSE.TXT for details.
+;
+;===------------------------------------------------------------------------===;
+;
+; This is an LLVMBuild description file for the components in this subdirectory.
+;
+; For more information on the LLVMBuild system, please see:
+;
+;   http://llvm.org/docs/LLVMBuild.html
+;
+;===------------------------------------------------------------------------===;
+[component_0]
+type = Tool
+name = llvm-objcopy
+parent = Tools
+required_libraries = Object MC

llvm/tools/llvm-objcopy/Object.cpp

@@ -0,0 +1,341 @@
+//===- Object.cpp -----------------------------------------------*- C++ -*-===//
+//
+//                      The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+#include "Object.h"
+#include "llvm-objcopy.h"
+
+using namespace llvm;
+using namespace object;
+using namespace ELF;
+
+template <class ELFT> void Segment::writeHeader(FileOutputBuffer &Out) const {
+  typedef typename ELFT::Ehdr Elf_Ehdr;
+  typedef typename ELFT::Phdr Elf_Phdr;
+
+  uint8_t *Buf = Out.getBufferStart();
+  Buf += sizeof(Elf_Ehdr) + Index * sizeof(Elf_Phdr);
+  Elf_Phdr &Phdr = *reinterpret_cast<Elf_Phdr *>(Buf);
+  Phdr.p_type = Type;
+  Phdr.p_flags = Flags;
+  Phdr.p_offset = Offset;
+  Phdr.p_vaddr = VAddr;
+  Phdr.p_paddr = PAddr;
+  Phdr.p_filesz = FileSize;
+  Phdr.p_memsz = MemSize;
+  Phdr.p_align = Align;
+}
+
+void Segment::finalize() {
+  auto FirstSec = firstSection();
+  if (FirstSec) {
+    // It is possible for a gap to be at the begining of a segment. Because of
+    // this we need to compute the new offset based on how large this gap was
+    // in the source file. Section layout should have already ensured that this
+    // space is not used for something else.
+    uint64_t OriginalOffset = Offset;
+    Offset = FirstSec->Offset - (FirstSec->OriginalOffset - OriginalOffset);
+  }
+}
+
+void SectionBase::finalize() {}
+
+template <class ELFT>
+void SectionBase::writeHeader(FileOutputBuffer &Out) const {
+  uint8_t *Buf = Out.getBufferStart();
+  Buf += HeaderOffset;
+  typename ELFT::Shdr &Shdr = *reinterpret_cast<typename ELFT::Shdr *>(Buf);
+  Shdr.sh_name = NameIndex;
+  Shdr.sh_type = Type;
+  Shdr.sh_flags = Flags;
+  Shdr.sh_addr = Addr;
+  Shdr.sh_offset = Offset;
+  Shdr.sh_size = Size;
+  Shdr.sh_link = Link;
+  Shdr.sh_info = Info;
+  Shdr.sh_addralign = Align;
+  Shdr.sh_entsize = EntrySize;
+}
+
+void Section::writeSection(FileOutputBuffer &Out) const {
+  if (Type == SHT_NOBITS)
+    return;
+  uint8_t *Buf = Out.getBufferStart() + Offset;
+  std::copy(std::begin(Contents), std::end(Contents), Buf);
+}
+
+void StringTableSection::addString(StringRef Name) {
+  StrTabBuilder.add(Name);
+  Size = StrTabBuilder.getSize();
+}
+
+uint32_t StringTableSection::findIndex(StringRef Name) const {
+  return StrTabBuilder.getOffset(Name);
+}
+
+void StringTableSection::finalize() { StrTabBuilder.finalize(); }
+
+void StringTableSection::writeSection(FileOutputBuffer &Out) const {
+  StrTabBuilder.write(Out.getBufferStart() + Offset);
+}
+
+// Returns true IFF a section is wholly inside the range of a segment
+static bool sectionWithinSegment(const SectionBase &Section,
+                                 const Segment &Segment) {
+  // If a section is empty it should be treated like it has a size of 1. This is
+  // to clarify the case when an empty section lies on a boundary between two
+  // segments and ensures that the section "belongs" to the second segment and
+  // not the first.
+  uint64_t SecSize = Section.Size ? Section.Size : 1;
+  return Segment.Offset <= Section.OriginalOffset &&
+         Segment.Offset + Segment.FileSize >= Section.OriginalOffset + SecSize;
+}
+
+template <class ELFT>
+void Object<ELFT>::readProgramHeaders(const ELFFile<ELFT> &ElfFile) {
+  uint32_t Index = 0;
+  for (const auto &Phdr : unwrapOrError(ElfFile.program_headers())) {
+    Segments.emplace_back(llvm::make_unique<Segment>());
+    Segment &Seg = *Segments.back();
+    Seg.Type = Phdr.p_type;
+    Seg.Flags = Phdr.p_flags;
+    Seg.Offset = Phdr.p_offset;
+    Seg.VAddr = Phdr.p_vaddr;
+    Seg.PAddr = Phdr.p_paddr;
+    Seg.FileSize = Phdr.p_filesz;
+    Seg.MemSize = Phdr.p_memsz;
+    Seg.Align = Phdr.p_align;
+    Seg.Index = Index++;
+    for (auto &Section : Sections) {
+      if (sectionWithinSegment(*Section, Seg)) {
+        Seg.addSection(&*Section);
+        if (!Section->ParentSegment ||
+            Section->ParentSegment->Offset > Seg.Offset) {
+          Section->ParentSegment = &Seg;
+        }
+      }
+    }
+  }
+}
+
+template <class ELFT>
+std::unique_ptr<SectionBase>
+Object<ELFT>::makeSection(const llvm::object::ELFFile<ELFT> &ElfFile,
+                          const Elf_Shdr &Shdr) {
+  ArrayRef<uint8_t> Data;
+  switch (Shdr.sh_type) {
+  case SHT_STRTAB:
+    return llvm::make_unique<StringTableSection>();
+  case SHT_NOBITS:
+    return llvm::make_unique<Section>(Data);
+  default:
+    Data = unwrapOrError(ElfFile.getSectionContents(&Shdr));
+    return llvm::make_unique<Section>(Data);
+  };
+}
+
+template <class ELFT>
+void Object<ELFT>::readSectionHeaders(const ELFFile<ELFT> &ElfFile) {
+  uint32_t Index = 0;
+  for (const auto &Shdr : unwrapOrError(ElfFile.sections())) {
+    if (Index == 0) {
+      ++Index;
+      continue;
+    }
+    SecPtr Sec = makeSection(ElfFile, Shdr);
+    Sec->Name = unwrapOrError(ElfFile.getSectionName(&Shdr));
+    Sec->Type = Shdr.sh_type;
+    Sec->Flags = Shdr.sh_flags;
+    Sec->Addr = Shdr.sh_addr;
+    Sec->Offset = Shdr.sh_offset;
+    Sec->OriginalOffset = Shdr.sh_offset;
+    Sec->Size = Shdr.sh_size;
+    Sec->Link = Shdr.sh_link;
+    Sec->Info = Shdr.sh_info;
+    Sec->Align = Shdr.sh_addralign;
+    Sec->EntrySize = Shdr.sh_entsize;
+    Sec->Index = Index++;
+    Sections.push_back(std::move(Sec));
+  }
+}
+
+template <class ELFT> size_t Object<ELFT>::totalSize() const {
+  // We already have the section header offset so we can calculate the total
+  // size by just adding up the size of each section header.
+  return SHOffset + Sections.size() * sizeof(Elf_Shdr) + sizeof(Elf_Shdr);
+}
+
+template <class ELFT> Object<ELFT>::Object(const ELFObjectFile<ELFT> &Obj) {
+  const auto &ElfFile = *Obj.getELFFile();
+  const auto &Ehdr = *ElfFile.getHeader();
+
+  std::copy(Ehdr.e_ident, Ehdr.e_ident + 16, Ident);
+  Type = Ehdr.e_type;
+  Machine = Ehdr.e_machine;
+  Version = Ehdr.e_version;
+  Entry = Ehdr.e_entry;
+  Flags = Ehdr.e_flags;
+
+  readSectionHeaders(ElfFile);
+  readProgramHeaders(ElfFile);
+
+  SectionNames =
+      dyn_cast<StringTableSection>(Sections[Ehdr.e_shstrndx - 1].get());
+}
+
+template <class ELFT> void Object<ELFT>::sortSections() {
+  // Put all sections in offset order. Maintain the ordering as closely as
+  // possible while meeting that demand however.
+  auto CompareSections = [](const SecPtr &A, const SecPtr &B) {
+    return A->OriginalOffset < B->OriginalOffset;
+  };
+  std::stable_sort(std::begin(Sections), std::end(Sections), CompareSections);
+}
+
+template <class ELFT> void Object<ELFT>::assignOffsets() {
+  // Decide file offsets and indexes.
+  size_t PhdrSize = Segments.size() * sizeof(Elf_Phdr);
+  // We can put section data after the ELF header and the program headers.
+  uint64_t Offset = sizeof(Elf_Ehdr) + PhdrSize;
+  uint64_t Index = 1;
+  for (auto &Section : Sections) {
+    // The segment can have a different alignment than the section. In the case
+    // that there is a parent segment then as long as we satisfy the alignment
+    // of the segment it should follow that that the section is aligned.
+    if (Section->ParentSegment) {
+      auto FirstInSeg = Section->ParentSegment->firstSection();
+      if (FirstInSeg == Section.get()) {
+        Offset = alignTo(Offset, Section->ParentSegment->Align);
+        // There can be gaps at the start of a segment before the first section.
+        // So first we assign the alignment of the segment and then assign the
+        // location of the section from there
+        Section->Offset =
+            Offset + Section->OriginalOffset - Section->ParentSegment->Offset;
+      }
+      // We should respect interstitial gaps of allocated sections. We *must*
+      // maintain the memory image so that addresses are preserved. As, with the
+      // exception of SHT_NOBITS sections at the end of segments, the memory
+      // image is a copy of the file image, we preserve the file image as well.
+      // There's a strange case where a thread local SHT_NOBITS can cause the
+      // memory image and file image to not be the same. This occurs, on some
+      // systems, when a thread local SHT_NOBITS is between two SHT_PROGBITS
+      // and the thread local SHT_NOBITS section is at the end of a TLS segment.
+      // In this case to faithfully copy the segment file image we must use
+      // relative offsets. In any other case this would be the same as using the
+      // relative addresses so this should maintian the memory image as desired.
+      Offset = FirstInSeg->Offset + Section->OriginalOffset -
+               FirstInSeg->OriginalOffset;
+    }
+    // Alignment should have already been handled by the above if statement if
+    // this if this section is in a segment. Technically this shouldn't do
+    // anything bad if the alignments of the sections are all correct and the
+    // file image isn't corrupted. Still in sticking with the motto "maintain
+    // the file image" we should avoid messing up the file image if the
+    // alignment disagrees with the file image.
+    if (!Section->ParentSegment && Section->Align)
+      Offset = alignTo(Offset, Section->Align);
+    Section->Offset = Offset;
+    Section->Index = Index++;
+    if (Section->Type != SHT_NOBITS)
+      Offset += Section->Size;
+  }
+  // 'offset' should now be just after all the section data so we should set the
+  // section header table offset to be exactly here. This spot might not be
+  // aligned properly however so we should align it as needed. For 32-bit ELF
+  // this needs to be 4-byte aligned and on 64-bit it needs to be 8-byte aligned
+  // so the size of ELFT::Addr is used to ensure this.
+  Offset = alignTo(Offset, sizeof(typename ELFT::Addr));
+  SHOffset = Offset;
+}
+
+template <class ELFT> void Object<ELFT>::finalize() {
+  for (auto &Section : Sections)
+    SectionNames->addString(Section->Name);
+
+  sortSections();
+  assignOffsets();
+
+  // Finalize SectionNames first so that we can assign name indexes.
+  SectionNames->finalize();
+  // Finally now that all offsets and indexes have been set we can finalize any
+  // remaining issues.
+  uint64_t Offset = SHOffset + sizeof(Elf_Shdr);
+  for (auto &Section : Sections) {
+    Section->HeaderOffset = Offset;
+    Offset += sizeof(Elf_Shdr);
+    Section->NameIndex = SectionNames->findIndex(Section->Name);
+    Section->finalize();
+  }
+
+  for (auto &Segment : Segments)
+    Segment->finalize();
+}
+
+template <class ELFT>
+void Object<ELFT>::writeHeader(FileOutputBuffer &Out) const {
+  uint8_t *Buf = Out.getBufferStart();
+  Elf_Ehdr &Ehdr = *reinterpret_cast<Elf_Ehdr *>(Buf);
+  std::copy(Ident, Ident + 16, Ehdr.e_ident);
+  Ehdr.e_type = Type;
+  Ehdr.e_machine = Machine;
+  Ehdr.e_version = Version;
+  Ehdr.e_entry = Entry;
+  Ehdr.e_phoff = sizeof(Elf_Ehdr);
+  Ehdr.e_shoff = SHOffset;
+  Ehdr.e_flags = Flags;
+  Ehdr.e_ehsize = sizeof(Elf_Ehdr);
+  Ehdr.e_phentsize = sizeof(Elf_Phdr);
+  Ehdr.e_phnum = Segments.size();
+  Ehdr.e_shentsize = sizeof(Elf_Shdr);
+  Ehdr.e_shnum = Sections.size() + 1;
+  Ehdr.e_shstrndx = SectionNames->Index;
+}
+
+template <class ELFT>
+void Object<ELFT>::writeProgramHeaders(FileOutputBuffer &Out) const {
+  for (auto &Phdr : Segments)
+    Phdr->template writeHeader<ELFT>(Out);
+}
+
+template <class ELFT>
+void Object<ELFT>::writeSectionHeaders(FileOutputBuffer &Out) const {
+  uint8_t *Buf = Out.getBufferStart() + SHOffset;
+  // This reference serves to write the dummy section header at the begining
+  // of the file.
+  Elf_Shdr &Shdr = *reinterpret_cast<Elf_Shdr *>(Buf);
+  Shdr.sh_name = 0;
+  Shdr.sh_type = SHT_NULL;
+  Shdr.sh_flags = 0;
+  Shdr.sh_addr = 0;
+  Shdr.sh_offset = 0;
+  Shdr.sh_size = 0;
+  Shdr.sh_link = 0;
+  Shdr.sh_info = 0;
+  Shdr.sh_addralign = 0;
+  Shdr.sh_entsize = 0;
+
+  for (auto &Section : Sections)
+    Section->template writeHeader<ELFT>(Out);
+}
+
+template <class ELFT>
+void Object<ELFT>::writeSectionData(FileOutputBuffer &Out) const {
+  for (auto &Section : Sections)
+    Section->writeSection(Out);
+}
+
+template <class ELFT> void Object<ELFT>::write(FileOutputBuffer &Out) {
+  writeHeader(Out);
+  writeProgramHeaders(Out);
+  writeSectionData(Out);
+  writeSectionHeaders(Out);
+}
+
+template class Object<ELF64LE>;
+template class Object<ELF64BE>;
+template class Object<ELF32LE>;
+template class Object<ELF32BE>;

llvm/tools/llvm-objcopy/Object.h

@@ -0,0 +1,150 @@
+//===- Object.h -------------------------------------------------*- C++ -*-===//
+//
+//                      The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_OBJCOPY_OBJECT_H
+#define LLVM_OBJCOPY_OBJECT_H
+
+#include "llvm/MC/StringTableBuilder.h"
+#include "llvm/Object/ELFObjectFile.h"
+#include "llvm/Support/FileOutputBuffer.h"
+
+#include <memory>
+#include <set>
+
+class Segment;
+
+class SectionBase {
+public:
+  llvm::StringRef Name;
+  Segment *ParentSegment = nullptr;
+  uint64_t HeaderOffset;
+  uint64_t OriginalOffset;
+  uint32_t Index;
+
+  uint64_t Addr = 0;
+  uint64_t Align = 1;
+  uint32_t EntrySize = 0;
+  uint64_t Flags = 0;
+  uint64_t Info = 0;
+  uint64_t Link = llvm::ELF::SHN_UNDEF;
+  uint64_t NameIndex = 0;
+  uint64_t Offset = 0;
+  uint64_t Size = 0;
+  uint64_t Type = llvm::ELF::SHT_NULL;
+
+  virtual ~SectionBase() {}
+  virtual void finalize();
+  template <class ELFT> void writeHeader(llvm::FileOutputBuffer &Out) const;
+  virtual void writeSection(llvm::FileOutputBuffer &Out) const = 0;
+};
+
+class Segment {
+private:
+  struct SectionCompare {
+    bool operator()(const SectionBase *Lhs, const SectionBase *Rhs) const {
+      // Some sections might have the same address if one of them is empty. To
+      // fix this we can use the lexicographic ordering on ->Addr and the
+      // address of the actully stored section.
+      if (Lhs->OriginalOffset == Rhs->OriginalOffset)
+        return Lhs < Rhs;
+      return Lhs->OriginalOffset < Rhs->OriginalOffset;
+    }
+  };
+
+  std::set<const SectionBase *, SectionCompare> Sections;
+
+public:
+  uint64_t Align;
+  uint64_t FileSize;
+  uint32_t Flags;
+  uint32_t Index;
+  uint64_t MemSize;
+  uint64_t Offset;
+  uint64_t PAddr;
+  uint64_t Type;
+  uint64_t VAddr;
+
+  void finalize();
+  const SectionBase *firstSection() const {
+    if (!Sections.empty())
+      return *Sections.begin();
+    return nullptr;
+  }
+  void addSection(const SectionBase *sec) { Sections.insert(sec); }
+  template <class ELFT> void writeHeader(llvm::FileOutputBuffer &Out) const;
+};
+
+class Section : public SectionBase {
+private:
+  llvm::ArrayRef<uint8_t> Contents;
+
+public:
+  Section(llvm::ArrayRef<uint8_t> Data) : Contents(Data) {}
+  void writeSection(llvm::FileOutputBuffer &Out) const override;
+};
+
+// This is just a wraper around a StringTableBuilder that implements SectionBase
+class StringTableSection : public SectionBase {
+private:
+  llvm::StringTableBuilder StrTabBuilder;
+
+public:
+  StringTableSection() : StrTabBuilder(llvm::StringTableBuilder::ELF) {
+    Type = llvm::ELF::SHT_STRTAB;
+  }
+
+  void addString(llvm::StringRef Name);
+  uint32_t findIndex(llvm::StringRef Name) const;
+  void finalize() override;
+  void writeSection(llvm::FileOutputBuffer &Out) const override;
+  static bool classof(const SectionBase *S) {
+    return S->Type == llvm::ELF::SHT_STRTAB;
+  }
+};
+
+template <class ELFT> class Object {
+private:
+  typedef std::unique_ptr<SectionBase> SecPtr;
+  typedef std::unique_ptr<Segment> SegPtr;
+
+  typedef typename ELFT::Shdr Elf_Shdr;
+  typedef typename ELFT::Ehdr Elf_Ehdr;
+  typedef typename ELFT::Phdr Elf_Phdr;
+
+  StringTableSection *SectionNames;
+  std::vector<SecPtr> Sections;
+  std::vector<SegPtr> Segments;
+
+  void sortSections();
+  void assignOffsets();
+  SecPtr makeSection(const llvm::object::ELFFile<ELFT> &ElfFile,
+                     const Elf_Shdr &Shdr);
+  void readProgramHeaders(const llvm::object::ELFFile<ELFT> &ElfFile);
+  void readSectionHeaders(const llvm::object::ELFFile<ELFT> &ElfFile);
+  void writeHeader(llvm::FileOutputBuffer &Out) const;
+  void writeProgramHeaders(llvm::FileOutputBuffer &Out) const;
+  void writeSectionData(llvm::FileOutputBuffer &Out) const;
+  void writeSectionHeaders(llvm::FileOutputBuffer &Out) const;
+
+public:
+  uint8_t Ident[16];
+  uint64_t Entry;
+  uint64_t SHOffset;
+  uint32_t Type;
+  uint32_t Machine;
+  uint32_t Version;
+  uint32_t Flags;
+
+  Object(const llvm::object::ELFObjectFile<ELFT> &Obj);
+  size_t totalSize() const;
+  void finalize();
+  void write(llvm::FileOutputBuffer &Out);
+};
+
+#endif

llvm/tools/llvm-objcopy/llvm-objcopy.cpp

@@ -0,0 +1,96 @@
+//===- llvm-objcopy.cpp -----------------------------------------*- C++ -*-===//
+//
+//                      The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+#include "llvm-objcopy.h"
+#include "Object.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/FileOutputBuffer.h"
+#include "llvm/Support/PrettyStackTrace.h"
+#include "llvm/Support/Signals.h"
+#include "llvm/Support/ToolOutputFile.h"
+
+#include <memory>
+#include <string>
+#include <system_error>
+
+using namespace llvm;
+using namespace object;
+using namespace ELF;
+
+// The name this program was invoked as.
+static StringRef ToolName;
+
+namespace llvm {
+
+LLVM_ATTRIBUTE_NORETURN void error(Twine Message) {
+  errs() << ToolName << ": " << Message << ".\n";
+  errs().flush();
+  exit(1);
+}
+
+LLVM_ATTRIBUTE_NORETURN void reportError(StringRef File, std::error_code EC) {
+  assert(EC);
+  errs() << ToolName << ": '" << File << "': " << EC.message() << ".\n";
+  exit(1);
+}
+
+LLVM_ATTRIBUTE_NORETURN void reportError(StringRef File, llvm::Error E) {
+  assert(E);
+  std::string Buf;
+  raw_string_ostream OS(Buf);
+  logAllUnhandledErrors(std::move(E), OS, "");
+  OS.flush();
+  errs() << ToolName << ": '" << File << "': " << Buf;
+  exit(1);
+}
+}
+
+cl::opt<std::string> InputFilename(cl::Positional, cl::desc("<input>"));
+cl::opt<std::string> OutputFilename(cl::Positional, cl::desc("<output>"),
+                                    cl::init("-"));
+
+void CopyBinary(const ELFObjectFile<ELF64LE> &ObjFile) {
+  std::unique_ptr<FileOutputBuffer> Buffer;
+  Object<ELF64LE> Obj{ObjFile};
+  Obj.finalize();
+  ErrorOr<std::unique_ptr<FileOutputBuffer>> BufferOrErr =
+      FileOutputBuffer::create(OutputFilename, Obj.totalSize(),
+                               FileOutputBuffer::F_executable);
+  if (BufferOrErr.getError())
+    error("failed to open " + OutputFilename);
+  else
+    Buffer = std::move(*BufferOrErr);
+  std::error_code EC;
+  if (EC)
+    report_fatal_error(EC.message());
+  Obj.write(*Buffer);
+  if (auto EC = Buffer->commit())
+    reportError(OutputFilename, EC);
+}
+
+int main(int argc, char **argv) {
+  // Print a stack trace if we signal out.
+  sys::PrintStackTraceOnErrorSignal(argv[0]);
+  PrettyStackTraceProgram X(argc, argv);
+  llvm_shutdown_obj Y; // Call llvm_shutdown() on exit.
+  cl::ParseCommandLineOptions(argc, argv, "llvm objcopy utility\n");
+  ToolName = argv[0];
+  if (InputFilename.empty()) {
+    cl::PrintHelpMessage();
+    return 2;
+  }
+  Expected<OwningBinary<Binary>> BinaryOrErr = createBinary(InputFilename);
+  if (!BinaryOrErr)
+    reportError(InputFilename, BinaryOrErr.takeError());
+  Binary &Binary = *BinaryOrErr.get().getBinary();
+  if (ELFObjectFile<ELF64LE> *o = dyn_cast<ELFObjectFile<ELF64LE>>(&Binary)) {
+    CopyBinary(*o);
+    return 0;
+  }
+  reportError(InputFilename, object_error::invalid_file_type);
+}

llvm/tools/llvm-objcopy/llvm-objcopy.h

@@ -0,0 +1,32 @@
+//===- llvm-objcopy.h -------------------------------------------*- C++ -*-===//
+//
+//                      The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+#ifndef LLVM_OBJCOPY_H
+#define LLVM_OBJCOPY_H
+
+#include "llvm/ADT/Twine.h"
+#include "llvm/Support/Error.h"
+
+namespace llvm {
+
+LLVM_ATTRIBUTE_NORETURN extern void error(Twine Message);
+
+// This is taken from llvm-readobj.
+// [see here](llvm/tools/llvm-readobj/llvm-readobj.h:38)
+template <class T> T unwrapOrError(Expected<T> EO) {
+  if (EO)
+    return *EO;
+  std::string Buf;
+  raw_string_ostream OS(Buf);
+  logAllUnhandledErrors(EO.takeError(), OS, "");
+  OS.flush();
+  error(Buf);
+}
+}
+
+#endif