[llvm-objcopy] [COFF] Fix handling of aux symbols for big objects

The aux symbols were stored in an opaque std::vector<uint8_t>,
with contents interpreted according to the rest of the symbol.

All aux symbol types but one fit in 18 bytes (sizeof(coff_symbol16)),
and if written to a bigobj, two extra padding bytes are written (as
sizeof(coff_symbol32) is 20). In the storage agnostic intermediate
representation, store the aux symbols as a series of coff_symbol16
sized opaque blobs. (In practice, all such aux symbols only consist
of one aux symbol, so this is more flexible than what reality needs.)

The special case is the file aux symbols, which are written in
potentially more than one aux symbol slot, without any padding,
as one single long string. This can't be stored in the same opaque
vector of fixed sized aux symbol entries. The file aux symbols will
occupy a different number of aux symbol slots depending on the type
of output object file. As nothing in the intermediate process needs
to have accurate raw symbol indices, updating that is moved into the
writer class.

Differential Revision: https://reviews.llvm.org/D57009

llvm-svn: 351947

Author: mstorsjo

llvm/test/tools/llvm-objcopy/COFF/Inputs/bigobj.o.gz

@@ -0,0 +1,35 @@
+RUN: %python %p/../Inputs/ungzip.py %p/Inputs/bigobj.o.gz > %t.in.o
+
+RUN: llvm-objdump -t %t.in.o | FileCheck %s --check-prefixes=SYMBOLS,SYMBOLS-BIG,SYMBOLS-ORIG
+
+# Do a plain copy, to check that section numbers in symbols referring
+# to sections outside of the small object format are handled correctly.
+RUN: llvm-objcopy -R '.text$4' %t.in.o %t.small.o
+RUN: llvm-objdump -t %t.in.o | FileCheck %s --check-prefixes=SYMBOLS,SYMBOLS-BIG,SYMBOLS-ORIG
+
+# Remove a section, making the section count fit into a small object.
+RUN: llvm-objcopy -R '.text$4' %t.in.o %t.small.o
+RUN: llvm-objdump -t %t.small.o | FileCheck %s --check-prefixes=SYMBOLS,SYMBOLS-SMALL,SYMBOLS-REMOVED-SMALL
+
+# Add a .gnu_debuglink section, forcing the object back to big format.
+RUN: llvm-objcopy --add-gnu-debuglink=%t.in.o %t.small.o %t.big.o
+ llvm-objdump -t %t.big.o | FileCheck %s --check-prefixes=SYMBOLS,SYMBOLS-BIG,SYMBOLS-REMOVED-BIG
+
+# In big object format, the .file symbol occupies one symbol table entry for
+# the auxillary data, but needs two entries in the small format, forcing the
+# raw symbol indices of later symbols to change.
+SYMBOLS:            SYMBOL TABLE:
+SYMBOLS-NEXT:       [ 0]{{.*}} (nx 1) {{.*}} .text
+SYMBOLS-NEXT:       AUX scnlen
+SYMBOLS-SMALL-NEXT: [ 2]{{.*}} (nx 2) {{.*}} .file
+SYMBOLS-BIG-NEXT:   [ 2]{{.*}} (nx 1) {{.*}} .file
+SYMBOLS-NEXT:       AUX abcdefghijklmnopqrs
+SYMBOLS-SMALL-NEXT: [ 5]{{.*}} (nx 0) {{.*}} foo
+SYMBOLS-BIG-NEXT:   [ 4]{{.*}} (nx 0) {{.*}} foo
+
+# Check that the section numbers outside of signed 16 bit int range
+# are represented properly. After removing one section, the section
+# numbers decrease.
+SYMBOLS-ORIG:          [ 5](sec 65280){{.*}} symbol65280
+SYMBOLS-REMOVED-SMALL: [ 6](sec 65279){{.*}} symbol65280
+SYMBOLS-REMOVED-BIG:   [ 5](sec 65279){{.*}} symbol65280

llvm/test/tools/llvm-objcopy/COFF/bigobj.test

@@ -1,4 +1,4 @@
-# RUN: %python %p/Inputs/ungzip.py %p/Inputs/many-sections.o.gz > %t
+# RUN: %python %p/../Inputs/ungzip.py %p/Inputs/many-sections.o.gz > %t
 # RUN: llvm-objcopy -R .text -R s0 -R s1 -R s2 -R s3 -R s4 -R s5 -R s6 %t %t2
 # RUN: llvm-readobj --sections %t2 | FileCheck --check-prefix=SECS %s
 

llvm/test/tools/llvm-objcopy/ELF/auto-remove-shndx.test

@@ -1,4 +1,4 @@
-RUN: %python %p/Inputs/ungzip.py %p/Inputs/many-sections.o.gz > %t
+RUN: %python %p/../Inputs/ungzip.py %p/Inputs/many-sections.o.gz > %t
 RUN: llvm-objcopy %t %t2
 RUN: llvm-readobj --file-headers %t2 | FileCheck --check-prefix=EHDR %s
 RUN: llvm-readobj --sections %t2 | FileCheck --check-prefix=SECS %s

llvm/test/tools/llvm-objcopy/ELF/many-sections.test

@@ -1,6 +1,6 @@
 # This test checks to see that a .symtab_shndx section is added to any binary
 # that needs it, even if the original was removed.
-RUN: %python %p/Inputs/ungzip.py %p/Inputs/many-sections.o.gz > %t
+RUN: %python %p/../Inputs/ungzip.py %p/Inputs/many-sections.o.gz > %t
 RUN: llvm-objcopy -R .symtab_shndx %t %t2
 RUN: llvm-readobj --sections %t2 | FileCheck %s
 

llvm/test/tools/llvm-objcopy/ELF/remove-shndx.test

@@ -1,7 +1,7 @@
 # This test makes sure that sections added at the end that don't have symbols
 # defined in them don't trigger the creation of a large index table.
 
-RUN: %python %p/Inputs/ungzip.py %p/Inputs/many-sections.o.gz > %t.0
+RUN: %python %p/../Inputs/ungzip.py %p/Inputs/many-sections.o.gz > %t.0
 RUN: cat %p/Inputs/alloc-symtab.o > %t
 RUN: llvm-objcopy -R .text -R s0 -R s1 -R s2 -R s3 -R s4 -R s5 -R s6 %t.0 %t2
 RUN: llvm-objcopy --add-section=.s0=%t --add-section=.s1=%t --add-section=.s2=%t %t2 %t2

llvm/test/tools/llvm-objcopy/ELF/strict-no-add.test

@@ -37,7 +37,7 @@ static uint64_t getNextRVA(const Object &Obj) {
     return 0;
   const Section &Last = Obj.getSections().back();
   return alignTo(Last.Header.VirtualAddress + Last.Header.VirtualSize,
-                 Obj.PeHeader.SectionAlignment);
+                 Obj.IsPE ? Obj.PeHeader.SectionAlignment : 1);
 }
 
 static uint32_t getCRC32(StringRef Data) {
@@ -74,8 +74,8 @@ static void addGnuDebugLink(Object &Obj, StringRef 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.SizeOfRawData = alignTo(Sec.Header.VirtualSize,
+                                     Obj.IsPE ? Obj.PeHeader.FileAlignment : 1);
   // Sec.Header.PointerToRawData is filled in by the writer.
   Sec.Header.PointerToRelocations = 0;
   Sec.Header.PointerToLinenumbers = 0;

llvm/test/tools/llvm-objcopy/ELF/Inputs/ungzip.py renamed to llvm/test/tools/llvm-objcopy/Inputs/ungzip.py

@@ -26,12 +26,8 @@ void Object::addSymbols(ArrayRef<Symbol> NewSymbols) {
 
 void Object::updateSymbols() {
   SymbolMap = DenseMap<size_t, Symbol *>(Symbols.size());
-  size_t RawSymIndex = 0;
-  for (Symbol &Sym : Symbols) {
+  for (Symbol &Sym : Symbols)
     SymbolMap[Sym.UniqueId] = &Sym;
-    Sym.RawIndex = RawSymIndex;
-    RawSymIndex += 1 + Sym.Sym.NumberOfAuxSymbols;
-  }
 }
 
 const Symbol *Object::findSymbol(size_t UniqueId) const {

llvm/tools/llvm-objcopy/COFF/COFFObjcopy.cpp

@@ -66,10 +66,24 @@ struct Section {
   std::vector<uint8_t> OwnedContents;
 };
 
+struct AuxSymbol {
+  AuxSymbol(ArrayRef<uint8_t> In) {
+    assert(In.size() == sizeof(Opaque));
+    std::copy(In.begin(), In.end(), Opaque);
+  }
+
+  ArrayRef<uint8_t> getRef() const {
+    return ArrayRef<uint8_t>(Opaque, sizeof(Opaque));
+  }
+
+  uint8_t Opaque[sizeof(object::coff_symbol16)];
+};
+
 struct Symbol {
   object::coff_symbol32 Sym;
   StringRef Name;
-  std::vector<uint8_t> AuxData;
+  std::vector<AuxSymbol> AuxData;
+  StringRef AuxFile;
   ssize_t TargetSectionId;
   ssize_t AssociativeComdatTargetSectionId = 0;
   Optional<size_t> WeakTargetSymbolId;
@@ -132,7 +146,7 @@ struct Object {
 
   ssize_t NextSectionUniqueId = 1; // Allow a UniqueId 0 to mean undefined.
 
-  // Update SymbolMap and RawIndex in each Symbol.
+  // Update SymbolMap.
   void updateSymbols();
 
   // Update SectionMap and Index in each Section.

llvm/tools/llvm-objcopy/COFF/Object.cpp

@@ -107,9 +107,24 @@ Error COFFReader::readSymbols(Object &Obj, bool IsBigObj) const {
                  *reinterpret_cast<const coff_symbol16 *>(SymRef.getRawPtr()));
     if (auto EC = COFFObj.getSymbolName(SymRef, Sym.Name))
       return errorCodeToError(EC);
-    Sym.AuxData = COFFObj.getSymbolAuxData(SymRef);
-    assert((Sym.AuxData.size() %
-            (IsBigObj ? sizeof(coff_symbol32) : sizeof(coff_symbol16))) == 0);
+
+    ArrayRef<uint8_t> AuxData = COFFObj.getSymbolAuxData(SymRef);
+    size_t SymSize = IsBigObj ? sizeof(coff_symbol32) : sizeof(coff_symbol16);
+    assert(AuxData.size() == SymSize * SymRef.getNumberOfAuxSymbols());
+    // The auxillary symbols are structs of sizeof(coff_symbol16) each.
+    // In the big object format (where symbols are coff_symbol32), each
+    // auxillary symbol is padded with 2 bytes at the end. Copy each
+    // auxillary symbol to the Sym.AuxData vector. For file symbols,
+    // the whole range of aux symbols are interpreted as one null padded
+    // string instead.
+    if (SymRef.isFileRecord())
+      Sym.AuxFile = StringRef(reinterpret_cast<const char *>(AuxData.data()),
+                              AuxData.size())
+                        .rtrim('\0');
+    else
+      for (size_t I = 0; I < SymRef.getNumberOfAuxSymbols(); I++)
+        Sym.AuxData.push_back(AuxData.slice(I * SymSize, sizeof(AuxSymbol)));
+
     // Find the unique id of the section
     if (SymRef.getSectionNumber() <=
         0) // Special symbol (undefined/absolute/debug)

llvm/tools/llvm-objcopy/COFF/Object.h

@@ -55,7 +55,8 @@ Error COFFWriter::finalizeSymbolContents() {
       if (Sym.Sym.NumberOfAuxSymbols == 1 &&
           Sym.Sym.StorageClass == IMAGE_SYM_CLASS_STATIC) {
         coff_aux_section_definition *SD =
-            reinterpret_cast<coff_aux_section_definition *>(Sym.AuxData.data());
+            reinterpret_cast<coff_aux_section_definition *>(
+                Sym.AuxData[0].Opaque);
         uint32_t SDSectionNumber;
         if (Sym.AssociativeComdatTargetSectionId == 0) {
           // Not a comdat associative section; just set the Number field to
@@ -79,7 +80,7 @@ Error COFFWriter::finalizeSymbolContents() {
     // we want to set. Only >= 1 would be required, but only == 1 makes sense.
     if (Sym.WeakTargetSymbolId && Sym.Sym.NumberOfAuxSymbols == 1) {
       coff_aux_weak_external *WE =
-          reinterpret_cast<coff_aux_weak_external *>(Sym.AuxData.data());
+          reinterpret_cast<coff_aux_weak_external *>(Sym.AuxData[0].Opaque);
       const Symbol *Target = Obj.findSymbol(*Sym.WeakTargetSymbolId);
       if (Target == nullptr)
         return createStringError(object_error::invalid_symbol_index,
@@ -141,13 +142,26 @@ size_t COFFWriter::finalizeStringTable() {
 
 template <class SymbolTy>
 std::pair<size_t, size_t> COFFWriter::finalizeSymbolTable() {
-  size_t SymTabSize = Obj.getSymbols().size() * sizeof(SymbolTy);
-  for (const auto &S : Obj.getSymbols())
-    SymTabSize += S.AuxData.size();
-  return std::make_pair(SymTabSize, sizeof(SymbolTy));
+  size_t RawSymIndex = 0;
+  for (auto &S : Obj.getMutableSymbols()) {
+    // Symbols normally have NumberOfAuxSymbols set correctly all the time.
+    // For file symbols, we need to know the output file's symbol size to be
+    // able to calculate the number of slots it occupies.
+    if (!S.AuxFile.empty())
+      S.Sym.NumberOfAuxSymbols =
+          alignTo(S.AuxFile.size(), sizeof(SymbolTy)) / sizeof(SymbolTy);
+    S.RawIndex = RawSymIndex;
+    RawSymIndex += 1 + S.Sym.NumberOfAuxSymbols;
+  }
+  return std::make_pair(RawSymIndex * sizeof(SymbolTy), sizeof(SymbolTy));
 }
 
 Error COFFWriter::finalize(bool IsBigObj) {
+  size_t SymTabSize, SymbolSize;
+  std::tie(SymTabSize, SymbolSize) = IsBigObj
+                                         ? finalizeSymbolTable<coff_symbol32>()
+                                         : finalizeSymbolTable<coff_symbol16>();
+
   if (Error E = finalizeRelocTargets())
     return E;
   if (Error E = finalizeSymbolContents())
@@ -199,10 +213,6 @@ Error COFFWriter::finalize(bool IsBigObj) {
   }
 
   size_t StrTabSize = finalizeStringTable();
-  size_t SymTabSize, SymbolSize;
-  std::tie(SymTabSize, SymbolSize) = IsBigObj
-                                         ? finalizeSymbolTable<coff_symbol32>()
-                                         : finalizeSymbolTable<coff_symbol16>();
 
   size_t PointerToSymbolTable = FileSize;
   // StrTabSize <= 4 is the size of an empty string table, only consisting
@@ -312,8 +322,23 @@ template <class SymbolTy> void COFFWriter::writeSymbolStringTables() {
     copySymbol<SymbolTy, coff_symbol32>(*reinterpret_cast<SymbolTy *>(Ptr),
                                         S.Sym);
     Ptr += sizeof(SymbolTy);
-    std::copy(S.AuxData.begin(), S.AuxData.end(), Ptr);
-    Ptr += S.AuxData.size();
+    if (!S.AuxFile.empty()) {
+      // For file symbols, just write the string into the aux symbol slots,
+      // assuming that the unwritten parts are initialized to zero in the memory
+      // mapped file.
+      std::copy(S.AuxFile.begin(), S.AuxFile.end(), Ptr);
+      Ptr += S.Sym.NumberOfAuxSymbols * sizeof(SymbolTy);
+    } else {
+      // For other auxillary symbols, write their opaque payload into one symbol
+      // table slot each. For big object files, the symbols are larger than the
+      // opaque auxillary symbol struct and we leave padding at the end of each
+      // entry.
+      for (const AuxSymbol &AuxSym : S.AuxData) {
+        ArrayRef<uint8_t> Ref = AuxSym.getRef();
+        std::copy(Ref.begin(), Ref.end(), Ptr);
+        Ptr += sizeof(SymbolTy);
+      }
+    }
   }
   if (StrTabBuilder.getSize() > 4 || !Obj.IsPE) {
     // Always write a string table in object files, even an empty one.

llvm/tools/llvm-objcopy/COFF/Reader.cpp

@@ -30,11 +30,11 @@ class COFFWriter {
   size_t SizeOfInitializedData;
   StringTableBuilder StrTabBuilder;
 
+  template <class SymbolTy> std::pair<size_t, size_t> finalizeSymbolTable();
   Error finalizeRelocTargets();
   Error finalizeSymbolContents();
   void layoutSections();
   size_t finalizeStringTable();
-  template <class SymbolTy> std::pair<size_t, size_t> finalizeSymbolTable();
 
   Error finalize(bool IsBigObj);