Reapply: [llvm-objcopy] [COFF] Implement --add-gnu-debuglink

This was reverted since it broke a couple buildbots. The reason
for the breakage is not yet known, but this time, the test has
got more diagnostics added, to hopefully allow figuring out
what goes wrong.

Differential Revision: https://reviews.llvm.org/D57007

llvm-svn: 351931

test/tools/llvm-objcopy/COFF/add-gnu-debuglink.test

@@ -0,0 +1,48 @@
+RUN: yaml2obj %p/Inputs/x86_64-exe.yaml > %t.in123.exe
+
+# Using a debuglink filename with a length that is a multiple of 4, to
+# showcase padding in CONTENTS below.
+
+RUN: llvm-objcopy --add-gnu-debuglink=%t.in123.exe %t.in123.exe %t.out.exe
+
+# Temporary debugging of issues with this test:
+RUN: ls -l %t.out.exe || true
+RUN: od -Ax -t x1 %t.out.exe || true
+RUN: llvm-readobj -sections %t.out.exe || true
+
+RUN: llvm-readobj -sections %t.out.exe | FileCheck %s --check-prefix=SECTIONS
+RUN: llvm-objdump -s %t.out.exe | FileCheck %s --check-prefix=CONTENTS
+
+# Show the last of the preexisting sections, which is used for choosing
+# a virtual address for the generated one.
+
+SECTIONS:        Section {
+SECTIONS:          Number: 4
+SECTIONS-NEXT:     Name: .pdata
+SECTIONS-NEXT:     VirtualSize: 0x18
+SECTIONS-NEXT:     VirtualAddress: 0x4000
+SECTIONS-NEXT:     RawDataSize: 512
+SECTIONS:        Section {
+SECTIONS-NEXT:     Number: 5
+SECTIONS-NEXT:     Name: .gnu_debuglink
+SECTIONS-NEXT:     VirtualSize: 0x2C
+SECTIONS-NEXT:     VirtualAddress: 0x5000
+SECTIONS-NEXT:     RawDataSize: 512
+SECTIONS-NEXT:     PointerToRawData:
+SECTIONS-NEXT:     PointerToRelocations:
+SECTIONS-NEXT:     PointerToLineNumbers:
+SECTIONS-NEXT:     RelocationCount:
+SECTIONS-NEXT:     LineNumberCount:
+SECTIONS-NEXT:     Characteristics [ (0x42000040)
+SECTIONS-NEXT:       IMAGE_SCN_CNT_INITIALIZED_DATA (0x40)
+SECTIONS-NEXT:       IMAGE_SCN_MEM_DISCARDABLE (0x2000000)
+SECTIONS-NEXT:       IMAGE_SCN_MEM_READ (0x40000000)
+SECTIONS-NEXT:     ]
+
+# Note: The last 4 bytes here are the crc of the referenced file - if the
+# yaml2obj generated file changes, this crc changes.
+
+CONTENTS: Contents of section .gnu_debuglink:
+CONTENTS:  40005000 6164642d 676e752d 64656275 676c696e  add-gnu-debuglin
+CONTENTS:  40005010 6b2e7465 73742e74 6d702e69 6e313233  k.test.tmp.in123
+CONTENTS:  40005020 2e657865 00000000 7929adc3           .exe

tools/llvm-objcopy/COFF/COFFObjcopy.cpp

@@ -17,6 +17,8 @@
 #include "llvm/Object/Binary.h"
 #include "llvm/Object/COFF.h"
 #include "llvm/Support/Errc.h"
+#include "llvm/Support/JamCRC.h"
+#include "llvm/Support/Path.h"
 #include <cassert>
 
 namespace llvm {
@@ -30,6 +32,61 @@ static bool isDebugSection(const Section &Sec) {
   return Sec.Name.startswith(".debug");
 }
 
+static uint64_t getNextRVA(const Object &Obj) {
+  if (Obj.getSections().empty())
+    return 0;
+  const Section &Last = Obj.getSections().back();
+  return alignTo(Last.Header.VirtualAddress + Last.Header.VirtualSize,
+                 Obj.PeHeader.SectionAlignment);
+}
+
+static uint32_t getCRC32(StringRef Data) {
+  JamCRC CRC;
+  CRC.update(ArrayRef<char>(Data.data(), Data.size()));
+  // The CRC32 value needs to be complemented because the JamCRC dosn't
+  // finalize the CRC32 value. It also dosn't negate the initial CRC32 value
+  // but it starts by default at 0xFFFFFFFF which is the complement of zero.
+  return ~CRC.getCRC();
+}
+
+static std::vector<uint8_t> createGnuDebugLinkSectionContents(StringRef File) {
+  ErrorOr<std::unique_ptr<MemoryBuffer>> LinkTargetOrErr =
+      MemoryBuffer::getFile(File);
+  if (!LinkTargetOrErr)
+    error("'" + File + "': " + LinkTargetOrErr.getError().message());
+  auto LinkTarget = std::move(*LinkTargetOrErr);
+  uint32_t CRC32 = getCRC32(LinkTarget->getBuffer());
+
+  StringRef FileName = sys::path::filename(File);
+  size_t CRCPos = alignTo(FileName.size() + 1, 4);
+  std::vector<uint8_t> Data(CRCPos + 4);
+  memcpy(Data.data(), FileName.data(), FileName.size());
+  support::endian::write32le(Data.data() + CRCPos, CRC32);
+  return Data;
+}
+
+static void addGnuDebugLink(Object &Obj, StringRef DebugLinkFile) {
+  uint32_t StartRVA = getNextRVA(Obj);
+
+  std::vector<Section> Sections;
+  Section Sec;
+  Sec.setOwnedContents(createGnuDebugLinkSectionContents(DebugLinkFile));
+  Sec.Name = ".gnu_debuglink";
+  Sec.Header.VirtualSize = Sec.getContents().size();
+  Sec.Header.VirtualAddress = StartRVA;
+  Sec.Header.SizeOfRawData =
+      alignTo(Sec.Header.VirtualSize, Obj.PeHeader.FileAlignment);
+  // Sec.Header.PointerToRawData is filled in by the writer.
+  Sec.Header.PointerToRelocations = 0;
+  Sec.Header.PointerToLinenumbers = 0;
+  // Sec.Header.NumberOfRelocations is filled in by the writer.
+  Sec.Header.NumberOfLinenumbers = 0;
+  Sec.Header.Characteristics = IMAGE_SCN_CNT_INITIALIZED_DATA |
+                               IMAGE_SCN_MEM_READ | IMAGE_SCN_MEM_DISCARDABLE;
+  Sections.push_back(Sec);
+  Obj.addSections(Sections);
+}
+
 static Error handleArgs(const CopyConfig &Config, Object &Obj) {
   // Perform the actual section removals.
   Obj.removeSections([&Config](const Section &Sec) {
@@ -109,6 +166,10 @@ static Error handleArgs(const CopyConfig &Config, Object &Obj) {
 
     return false;
   });
+
+  if (!Config.AddGnuDebugLink.empty())
+    addGnuDebugLink(Obj, Config.AddGnuDebugLink);
+
   return Error::success();
 }
 

tools/llvm-objcopy/COFF/Object.cpp

@@ -129,7 +129,7 @@ void Object::removeSections(function_ref<bool(const Section &)> ToRemove) {
 void Object::truncateSections(function_ref<bool(const Section &)> ToTruncate) {
   for (Section &Sec : Sections) {
     if (ToTruncate(Sec)) {
-      Sec.Contents = ArrayRef<uint8_t>();
+      Sec.clearContents();
       Sec.Relocs.clear();
       Sec.Header.SizeOfRawData = 0;
     }

tools/llvm-objcopy/COFF/Object.h

@@ -35,11 +35,35 @@ struct Relocation {
 
 struct Section {
   object::coff_section Header;
-  ArrayRef<uint8_t> Contents;
   std::vector<Relocation> Relocs;
   StringRef Name;
   ssize_t UniqueId;
   size_t Index;
+
+  ArrayRef<uint8_t> getContents() const {
+    if (!OwnedContents.empty())
+      return OwnedContents;
+    return ContentsRef;
+  }
+
+  void setContentsRef(ArrayRef<uint8_t> Data) {
+    OwnedContents.clear();
+    ContentsRef = Data;
+  }
+
+  void setOwnedContents(std::vector<uint8_t> &&Data) {
+    ContentsRef = ArrayRef<uint8_t>();
+    OwnedContents = std::move(Data);
+  }
+
+  void clearContents() {
+    ContentsRef = ArrayRef<uint8_t>();
+    OwnedContents.clear();
+  }
+
+private:
+  ArrayRef<uint8_t> ContentsRef;
+  std::vector<uint8_t> OwnedContents;
 };
 
 struct Symbol {

tools/llvm-objcopy/COFF/Reader.cpp

@@ -69,8 +69,10 @@ Error COFFReader::readSections(Object &Obj) const {
     Sections.push_back(Section());
     Section &S = Sections.back();
     S.Header = *Sec;
-    if (auto EC = COFFObj.getSectionContents(Sec, S.Contents))
+    ArrayRef<uint8_t> Contents;
+    if (auto EC = COFFObj.getSectionContents(Sec, Contents))
       return errorCodeToError(EC);
+    S.setContentsRef(Contents);
     ArrayRef<coff_relocation> Relocs = COFFObj.getRelocations(Sec);
     for (const coff_relocation &R : Relocs)
       S.Relocs.push_back(R);

tools/llvm-objcopy/COFF/Writer.cpp

@@ -286,14 +286,15 @@ void COFFWriter::writeHeaders(bool IsBigObj) {
 void COFFWriter::writeSections() {
   for (const auto &S : Obj.getSections()) {
     uint8_t *Ptr = Buf.getBufferStart() + S.Header.PointerToRawData;
-    std::copy(S.Contents.begin(), S.Contents.end(), Ptr);
+    ArrayRef<uint8_t> Contents = S.getContents();
+    std::copy(Contents.begin(), Contents.end(), Ptr);
 
     // For executable sections, pad the remainder of the raw data size with
     // 0xcc, which is int3 on x86.
     if ((S.Header.Characteristics & IMAGE_SCN_CNT_CODE) &&
-        S.Header.SizeOfRawData > S.Contents.size())
-      memset(Ptr + S.Contents.size(), 0xcc,
-             S.Header.SizeOfRawData - S.Contents.size());
+        S.Header.SizeOfRawData > Contents.size())
+      memset(Ptr + Contents.size(), 0xcc,
+             S.Header.SizeOfRawData - Contents.size());
 
     Ptr += S.Header.SizeOfRawData;
     for (const auto &R : S.Relocs) {