[WebAssembly] MC: Create wasm data segments based on MCSections

[sbc100]

Summary

This means that we can honor -fdata-sections rather than always creating
a segment for each symbol.

It also allows for a followup change to add .init_array and friends.

[sbc100]

More section types

[dschuff]

Should the patch title be "create data *segments* based on MCSections"?

lib/MC/WasmObjectWriter.cpp

515

Does this mean we don't support the .p2align directive?
If so, we should have a TODO to fix it. Or do we just expect it to get converted and we should never see this (in other words, can it be an assert instead)?

[sbc100]

• support custom data sections

[sbc100]

Added support for explicit custom section names, and added new test

lib/MC/WasmObjectWriter.cpp

515

I'm not sure why this is here but we haven't been seeing this show up in testing yet. I'm only moving this code. I'd rather not also change it in this CL.

[sbc100]

• rename test

include/llvm/MC/MCSectionWasm.h

private:
 
   const MCSymbolWasm *Group;
 
   // The offset of the MC function/data section in the wasm code/data section.
   // For data relocations the offset is relative to start of the data payload
   // itself and does not include the size of the section header.
   uint64_t SectionOffset;
 
+  // For data sections, this is the offset of the corresponding wasm data
+  // segment
+  uint64_t MemoryOffset;
+
   friend class MCContext;
   MCSectionWasm(StringRef Section, unsigned type, SectionKind K,
                 const MCSymbolWasm *group, unsigned UniqueID, MCSymbol *Begin)
       : MCSection(SV_Wasm, K, Begin), SectionName(Section), Type(type),
         UniqueID(UniqueID), Group(group), SectionOffset(0) {}
 
   void setSectionName(StringRef Name) { SectionName = Name; }
 
public:
   bool isVirtualSection() const override;
 
   bool isUnique() const { return UniqueID != ~0U; }
   unsigned getUniqueID() const { return UniqueID; }
 
   uint64_t getSectionOffset() const { return SectionOffset; }
   void setSectionOffset(uint64_t Offset) { SectionOffset = Offset; }
 
+  uint32_t getMemoryOffset() const { return MemoryOffset; }
+  void setMemoryOffset(uint32_t Offset) { MemoryOffset = Offset; }
+
   static bool classof(const MCSection *S) { return S->getVariant() == SV_Wasm; }
 };
 
 } // end namespace llvm
 
 #endif

lib/CodeGen/TargetLoweringObjectFileImpl.cpp

static MCSectionWasm *selectWasmSectionForGlobal(
     const TargetMachine &TM, bool EmitUniqueSection, unsigned *NextUniqueID) {
   StringRef Group = "";
   if (getWasmComdat(GO))
     llvm_unreachable("comdat not yet supported for wasm");
 
   bool UniqueSectionNames = TM.getUniqueSectionNames();
   SmallString<128> Name = getSectionPrefixForGlobal(Kind);
 
+  uint32_t Type = wasm::WASM_SEC_DATA;
   if (const auto *F = dyn_cast<Function>(GO)) {
     const auto &OptionalPrefix = F->getSectionPrefix();
     if (OptionalPrefix)
       Name += *OptionalPrefix;
+    Type = wasm::WASM_SEC_CODE;
   }
 
   if (EmitUniqueSection && UniqueSectionNames) {
     Name.push_back('.');
     TM.getNameWithPrefix(Name, GO, Mang, true);
   }
   unsigned UniqueID = MCContext::GenericSectionID;
   if (EmitUniqueSection && !UniqueSectionNames) {
     UniqueID = *NextUniqueID;
     (*NextUniqueID)++;
   }
-  return Ctx.getWasmSection(Name, /*Type=*/0, Group, UniqueID);
+  return Ctx.getWasmSection(Name, Type, Group, UniqueID);
 }
 
 MCSection *TargetLoweringObjectFileWasm::SelectSectionForGlobal(
     const GlobalObject *GO, SectionKind Kind, const TargetMachine &TM) const {
 
   if (Kind.isCommon())
     report_fatal_error("mergable sections not supported yet on wasm");
 

lib/MC/MCObjectFileInfo.cpp

void MCObjectFileInfo::initCOFFMCObjectFileInfo(const Triple &T) {
   StackMapSection = Ctx->getCOFFSection(".llvm_stackmaps",
                                         COFF::IMAGE_SCN_CNT_INITIALIZED_DATA |
                                             COFF::IMAGE_SCN_MEM_READ,
                                         SectionKind::getReadOnly());
 }
 
 void MCObjectFileInfo::initWasmMCObjectFileInfo(const Triple &T) {
   // TODO: Set the section types and flags.
-  TextSection = Ctx->getWasmSection(".text", 0);
-  DataSection = Ctx->getWasmSection(".data", 0);
+  TextSection = Ctx->getWasmSection(".text", wasm::WASM_SEC_CODE);
+  DataSection = Ctx->getWasmSection(".data", wasm::WASM_SEC_DATA);
 
   // TODO: Set the section types and flags.
   DwarfLineSection = Ctx->getWasmSection(".debug_line", 0);
   DwarfStrSection = Ctx->getWasmSection(".debug_str", 0);
   DwarfLocSection = Ctx->getWasmSection(".debug_loc", 0);
   DwarfAbbrevSection = Ctx->getWasmSection(".debug_abbrev", 0, "section_abbrev");
   DwarfARangesSection = Ctx->getWasmSection(".debug_aranges", 0);
   DwarfRangesSection = Ctx->getWasmSection(".debug_ranges", 0, "debug_range");

lib/MC/MCWasmStreamer.cpp

void MCWasmStreamer::EmitValueToAlignment(unsigned ByteAlignment, int64_t Value,
                                           unsigned ValueSize,
                                           unsigned MaxBytesToEmit) {
   MCObjectStreamer::EmitValueToAlignment(ByteAlignment, Value, ValueSize,
                                          MaxBytesToEmit);
 }
 
 void MCWasmStreamer::EmitIdent(StringRef IdentString) {
   MCSection *Comment = getAssembler().getContext().getWasmSection(
-      ".comment", 0, 0);
+      ".comment", wasm::WASM_SEC_DATA);
   PushSection();
   SwitchSection(Comment);
   if (!SeenIdent) {
     EmitIntValue(0, 1);
     SeenIdent = true;
   }
   EmitBytes(IdentString);
   EmitIntValue(0, 1);

lib/MC/WasmObjectWriter.cpp

case wasm::R_WEBASSEMBLY_MEMORY_ADDR_I32:
       return true;
     default:
       return false;
     }
   }
 
   void print(raw_ostream &Out) const {
     Out << "Off=" << Offset << ", Sym=" << *Symbol << ", Addend=" << Addend
-        << ", Type=" << Type << ", FixupSection=" << FixupSection;
+        << ", Type=" << Type
+        << ", FixupSection=" << FixupSection->getSectionName();
   }
 
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
   LLVM_DUMP_METHOD void dump() const { print(dbgs()); }
 #endif
 };
 
 #if !defined(NDEBUG)
WasmObjectWriter::getProvisionalValue(const WasmRelocationEntry &RelEntry) {
   uint64_t Address = Global.InitialValue + RelEntry.Addend;
 
   // Ignore overflow. LLVM allows address arithmetic to silently wrap.
   uint32_t Value = Address;
 
   return Value;
 }
 
+static void addData(SmallVectorImpl<char> &DataBytes,
+                    MCSectionWasm &DataSection, uint32_t &DataAlignment) {
+  DataBytes.resize(alignTo(DataBytes.size(), DataSection.getAlignment()));
+  DataAlignment = std::max(DataAlignment, DataSection.getAlignment());
+  DEBUG(errs() << "addData: " << DataSection.getSectionName() << "\n");
+
+  for (const MCFragment &Frag : DataSection) {
+    if (Frag.hasInstructions())
+      report_fatal_error("only data supported in data sections");
+
+    if (auto *Align = dyn_cast<MCAlignFragment>(&Frag)) {
+      if (Align->getValueSize() != 1)
+        report_fatal_error("only byte values supported for alignment");
+      // If nops are requested, use zeros, as this is the data section.
+      uint8_t Value = Align->hasEmitNops() ? 0 : Align->getValue();
+      uint64_t Size = std::min<uint64_t>(alignTo(DataBytes.size(),
+                                                 Align->getAlignment()),
+                                         DataBytes.size() +
+                                             Align->getMaxBytesToEmit());
+      DataBytes.resize(Size, Value);
+    } else if (auto *Fill = dyn_cast<MCFillFragment>(&Frag)) {
+      DataBytes.insert(DataBytes.end(), Fill->getSize(), Fill->getValue());
+    } else {
+      const auto &DataFrag = cast<MCDataFragment>(Frag);
+      const SmallVectorImpl<char> &Contents = DataFrag.getContents();
+
+      DataBytes.insert(DataBytes.end(), Contents.begin(), Contents.end());
+    }
+  }
+
+  DEBUG(dbgs() << "addData -> " << DataBytes.size() << "\n");
+}
+
 uint32_t WasmObjectWriter::getRelocationIndexValue(
     const WasmRelocationEntry &RelEntry) {
   switch (RelEntry.Type) {
   case wasm::R_WEBASSEMBLY_TABLE_INDEX_SLEB:
   case wasm::R_WEBASSEMBLY_TABLE_INDEX_I32:
     if (!IndirectSymbolIndices.count(RelEntry.Symbol))
       report_fatal_error("symbol not found table index space: " +
                          RelEntry.Symbol->getName());
void WasmObjectWriter::writeCodeSection(
   for (const WasmFunction &Func : Functions) {
     auto &FuncSection = static_cast<MCSectionWasm &>(Func.Sym->getSection());
 
     int64_t Size = 0;
     if (!Func.Sym->getSize()->evaluateAsAbsolute(Size, Layout))
       report_fatal_error(".size expression must be evaluatable");
 
     encodeULEB128(Size, getStream());
-
     FuncSection.setSectionOffset(getStream().tell() - Section.ContentsOffset);
-
     Asm.writeSectionData(&FuncSection, Layout);
   }
 
   // Apply fixups.
   applyRelocations(CodeRelocations, Section.ContentsOffset);
 
   endSection(Section);
 }
if (!DataFrag.getFixups().empty())
       report_fatal_error("fixups not supported in .stack_pointer");
     const SmallVectorImpl<char> &Contents = DataFrag.getContents();
     if (Contents.size() != 4)
       report_fatal_error("only one entry supported in .stack_pointer");
     HasStackPointer = true;
     StackPointerGlobal = NumGlobalImports + *(const int32_t *)Contents.data();
   }
 
+  for (MCSection &Sec : Asm) {
+    auto &Section = static_cast<MCSectionWasm &>(Sec);
+    if (Section.getType() != wasm::WASM_SEC_DATA)
+      continue;
+
+    DataSize = alignTo(DataSize, Section.getAlignment());
+    DataSegments.emplace_back();
+    WasmDataSegment &Segment = DataSegments.back();
+    Segment.Offset = DataSize;
+    Segment.Section = &Section;
+    addData(Segment.Data, Section, DataAlignment);
+    DataSize += Segment.Data.size();
+    Section.setMemoryOffset(Segment.Offset);
+  }
+
   // Handle regular defined and undefined symbols.
   for (const MCSymbol &S : Asm.symbols()) {
     // Ignore unnamed temporary symbols, which aren't ever exported, imported,
     // or used in relocations.
     if (S.isTemporary() && S.getName().empty())
       continue;
 
     const auto &WS = static_cast<const MCSymbolWasm &>(S);
if (WS.isFunction()) {
       }
     } else {
       if (WS.isTemporary() && !WS.getSize())
         continue;
 
       if (!WS.isDefined(/*SetUsed=*/false))
         continue;
 
-      if (WS.getOffset() != 0)
-        report_fatal_error("data sections must contain one variable each: " +
-                           WS.getName());
       if (!WS.getSize())
         report_fatal_error("data symbols must have a size set with .size: " +
                            WS.getName());
 
       int64_t Size = 0;
       if (!WS.getSize()->evaluateAsAbsolute(Size, Layout))
         report_fatal_error(".size expression must be evaluatable");
 
-      auto &DataSection = static_cast<MCSectionWasm &>(WS.getSection());
-
-      if (uint64_t(Size) != Layout.getSectionFileSize(&DataSection))
-        report_fatal_error("data sections must contain at most one variable");
-
-      DataAlignment = std::max(DataAlignment, DataSection.getAlignment());
-
-      DataSegments.emplace_back();
-      WasmDataSegment &Segment = DataSegments.back();
-
-      DataSize = alignTo(DataSize, DataSection.getAlignment());
-      Segment.Offset = DataSize;
-      Segment.Section = &DataSection;
-
       // For each global, prepare a corresponding wasm global holding its
       // address.  For externals these will also be named exports.
       Index = NumGlobalImports + Globals.size();
+      auto &DataSection = static_cast<MCSectionWasm &>(WS.getSection());
 
       WasmGlobal Global;
       Global.Type = PtrType;
       Global.IsMutable = false;
       Global.HasImport = false;
-      Global.InitialValue = DataSize;
+      Global.InitialValue = DataSection.getMemoryOffset() + Layout.getSymbolOffset(WS);
       Global.ImportIndex = 0;
       SymbolIndices[&WS] = Index;
       DEBUG(dbgs() << "  -> global index: " << Index << "\n");
       Globals.push_back(Global);
-
-      for (const MCFragment &Frag : DataSection) {
-        if (Frag.hasInstructions())
-          report_fatal_error("only data supported in data sections");
-
-        if (auto *Align = dyn_cast<MCAlignFragment>(&Frag)) {
-          if (Align->getValueSize() != 1)
-            report_fatal_error("only byte values supported for alignment");
-          // If nops are requested, use zeros, as this is the data section.
-          uint8_t Value = Align->hasEmitNops() ? 0 : Align->getValue();
-          uint64_t Size = std::min<uint64_t>(
-              alignTo(Segment.Data.size(), Align->getAlignment()),
-              Segment.Data.size() + Align->getMaxBytesToEmit());
-          Segment.Data.resize(Size, Value);
-        } else if (auto *Fill = dyn_cast<MCFillFragment>(&Frag)) {
-          Segment.Data.insert(Segment.Data.end(), Fill->getSize(), Fill->getValue());
-        } else {
-          const auto &DataFrag = cast<MCDataFragment>(Frag);
-          const SmallVectorImpl<char> &Contents = DataFrag.getContents();
-
-          Segment.Data.insert(Segment.Data.end(), Contents.begin(),
-                              Contents.end());
-        }
-      }
-      DataSize += Segment.Data.size();
     }
 
     // If the symbol is visible outside this translation unit, export it.
     if ((WS.isExternal() && WS.isDefined(/*SetUsed=*/false))) {
       WasmExport Export;
       Export.FieldName = WS.getName();
       Export.Index = Index;
       if (WS.isFunction())