[BOLT] Overwrite .eh_frame and .gcc_except_table (llvm#116755)

Under --use-old-text or --strict, we completely rewrite contents of EH
frames and exception tables sections. If new contents of either section
do not exceed the size of the original section, rewrite the section
in-place.

Author: maksfb

bolt/include/bolt/Core/BinarySection.h

@@ -87,6 +87,7 @@ class BinarySection {
                                    // been renamed)
   uint64_t OutputAddress{0};       // Section address for the rewritten binary.
   uint64_t OutputSize{0};          // Section size in the rewritten binary.
+                                   // Can exceed OutputContents with padding.
   uint64_t OutputFileOffset{0};    // File offset in the rewritten binary file.
   StringRef OutputContents;        // Rewritten section contents.
   const uint64_t SectionNumber;    // Order in which the section was created.
@@ -474,6 +475,11 @@ class BinarySection {
   /// Use name \p SectionName for the section during the emission.
   void emitAsData(MCStreamer &Streamer, const Twine &SectionName) const;
 
+  /// Write finalized contents of the section. If OutputSize exceeds the size of
+  /// the OutputContents, append zero padding to the stream and return the
+  /// number of byte written which should match the OutputSize.
+  uint64_t write(raw_ostream &OS) const;
+
   using SymbolResolverFuncTy = llvm::function_ref<uint64_t(const MCSymbol *)>;
 
   /// Flush all pending relocations to patch original contents of sections
@@ -497,6 +503,9 @@ class BinarySection {
     IsFinalized = true;
   }
 
+  /// When writing section contents, add \p PaddingSize zero bytes at the end.
+  void addPadding(uint64_t PaddingSize) { OutputSize += PaddingSize; }
+
   /// Reorder the contents of this section according to /p Order.  If
   /// /p Inplace is true, the entire contents of the section is reordered,
   /// otherwise the new contents contain only the reordered data.

bolt/lib/Core/BinarySection.cpp

@@ -142,6 +142,15 @@ void BinarySection::emitAsData(MCStreamer &Streamer,
     Streamer.emitLabel(BC.Ctx->getOrCreateSymbol("__hot_data_end"));
 }
 
+uint64_t BinarySection::write(raw_ostream &OS) const {
+  const uint64_t NumValidContentBytes =
+      std::min<uint64_t>(getOutputContents().size(), getOutputSize());
+  OS.write(getOutputContents().data(), NumValidContentBytes);
+  if (getOutputSize() > NumValidContentBytes)
+    OS.write_zeros(getOutputSize() - NumValidContentBytes);
+  return getOutputSize();
+}
+
 void BinarySection::flushPendingRelocations(raw_pwrite_stream &OS,
                                             SymbolResolverFuncTy Resolver) {
   if (PendingRelocations.empty() && Patches.empty())

bolt/lib/Rewrite/RewriteInstance.cpp

@@ -3887,6 +3887,43 @@ void RewriteInstance::mapCodeSections(BOLTLinker::SectionMapper MapSection) {
 
 void RewriteInstance::mapAllocatableSections(
     BOLTLinker::SectionMapper MapSection) {
+
+  if (opts::UseOldText || opts::StrictMode) {
+    auto tryRewriteSection = [&](BinarySection &OldSection,
+                                 BinarySection &NewSection) {
+      if (OldSection.getSize() < NewSection.getOutputSize())
+        return;
+
+      BC->outs() << "BOLT-INFO: rewriting " << OldSection.getName()
+                 << " in-place\n";
+
+      NewSection.setOutputAddress(OldSection.getAddress());
+      NewSection.setOutputFileOffset(OldSection.getInputFileOffset());
+      MapSection(NewSection, OldSection.getAddress());
+
+      // Pad contents with zeros.
+      NewSection.addPadding(OldSection.getSize() - NewSection.getOutputSize());
+
+      // Prevent the original section name from appearing in the section header
+      // table.
+      OldSection.setAnonymous(true);
+    };
+
+    if (EHFrameSection) {
+      BinarySection *NewEHFrameSection =
+          getSection(getNewSecPrefix() + getEHFrameSectionName());
+      assert(NewEHFrameSection && "New contents expected for .eh_frame");
+      tryRewriteSection(*EHFrameSection, *NewEHFrameSection);
+    }
+    BinarySection *EHSection = getSection(".gcc_except_table");
+    BinarySection *NewEHSection =
+        getSection(getNewSecPrefix() + ".gcc_except_table");
+    if (EHSection) {
+      assert(NewEHSection && "New contents expected for .gcc_except_table");
+      tryRewriteSection(*EHSection, *NewEHSection);
+    }
+  }
+
   // Allocate read-only sections first, then writable sections.
   enum : uint8_t { ST_READONLY, ST_READWRITE };
   for (uint8_t SType = ST_READONLY; SType <= ST_READWRITE; ++SType) {
@@ -4164,7 +4201,6 @@ void RewriteInstance::rewriteNoteSections() {
     // New section size.
     uint64_t Size = 0;
     bool DataWritten = false;
-    uint8_t *SectionData = nullptr;
     // Copy over section contents unless it's one of the sections we overwrite.
     if (!willOverwriteSection(SectionName)) {
       Size = Section.sh_size;
@@ -4196,12 +4232,7 @@ void RewriteInstance::rewriteNoteSections() {
     if (BSec->getAllocAddress()) {
       assert(!DataWritten && "Writing section twice.");
       (void)DataWritten;
-      SectionData = BSec->getOutputData();
-
-      LLVM_DEBUG(dbgs() << "BOLT-DEBUG: " << (Size ? "appending" : "writing")
-                        << " contents to section " << SectionName << '\n');
-      OS.write(reinterpret_cast<char *>(SectionData), BSec->getOutputSize());
-      Size += BSec->getOutputSize();
+      Size += BSec->write(OS);
     }
 
     BSec->setOutputFileOffset(NextAvailableOffset);
@@ -4232,8 +4263,7 @@ void RewriteInstance::rewriteNoteSections() {
                << " of size " << Section.getOutputSize() << " at offset 0x"
                << Twine::utohexstr(Section.getOutputFileOffset()) << '\n');
 
-    OS.write(Section.getOutputContents().data(), Section.getOutputSize());
-    NextAvailableOffset += Section.getOutputSize();
+    NextAvailableOffset += Section.write(OS);
   }
 }
 
@@ -4347,6 +4377,10 @@ RewriteInstance::getOutputSections(ELFObjectFile<ELFT> *File,
     BinarySection *BinSec = BC->getSectionForSectionRef(SecRef);
     assert(BinSec && "Matching BinarySection should exist.");
 
+    // Exclude anonymous sections.
+    if (BinSec->isAnonymous())
+      continue;
+
     addSection(Section, *BinSec);
   }
 
@@ -5699,8 +5733,8 @@ void RewriteInstance::rewriteFile() {
                  << Twine::utohexstr(Section.getAllocAddress()) << "\n of size "
                  << Section.getOutputSize() << "\n at offset "
                  << Section.getOutputFileOffset() << '\n';
-    OS.pwrite(reinterpret_cast<const char *>(Section.getOutputData()),
-              Section.getOutputSize(), Section.getOutputFileOffset());
+    OS.seek(Section.getOutputFileOffset());
+    Section.write(OS);
   }
 
   for (BinarySection &Section : BC->allocatableSections())

bolt/test/eh-frame-overwrite.test

@@ -0,0 +1,8 @@
+# Check that llvm-bolt can overwrite .eh_frame section in-place.
+
+REQUIRES: system-linux
+
+RUN: %clang %cflags %p/Inputs/hello.c -o %t -Wl,-q
+RUN: llvm-bolt %t -o %t.bolt --strict | FileCheck %s
+
+CHECK: rewriting .eh_frame in-place