[WebAssembly] Add support for named data sections in wasm binaries

[sbc100]

Summary

Followup to https://reviews.llvm.org/D91769 which added support
for names globals.

[tlively]

llvm/lib/Object/WasmObjectFile.cpp

378

It would be good to give a more descriptive name to T now that it is no longer used directly after it is declared.

lld/test/wasm/call-indirect.ll

 ; CHECK-NEXT:         Name:            foo
 ; CHECK-NEXT:       - Index:           3
 ; CHECK-NEXT:         Name:            _start
 ; CHECK-NEXT:       - Index:           4
 ; CHECK-NEXT:         Name:            call_ptr
 ; CHECK-NEXT:     GlobalNames:
 ; CHECK-NEXT:       - Index:           0
 ; CHECK-NEXT:         Name:            __stack_pointer
+; CHECK-NEXT:     DataSegmentNames:
+; CHECK-NEXT:       - Index:           0
+; CHECK-NEXT:         Name:            .data
 ; CHECK-NEXT: ...

lld/test/wasm/data-segment-merging.ll

 ; MERGE-NEXT:  - Type:            CUSTOM
 ; MERGE-NEXT:    Name:            name
 ; MERGE-NEXT:    FunctionNames:
 ; MERGE-NEXT:      - Index:           0
 ; MERGE-NEXT:        Name:            __wasm_call_ctors
 ; MERGE-NEXT:    GlobalNames:
 ; MERGE-NEXT:      - Index:           0
 ; MERGE-NEXT:        Name:            __stack_pointer
-; MERGE-NOT:       - Index:
+; MERGE-NEXT:    DataSegmentNames:
+; MERGE-NEXT:      - Index:           0
+; MERGE-NEXT:        Name:            .rodata
 
 ; RUN: wasm-ld -no-gc-sections --no-entry --no-merge-data-segments -o %t.separate.wasm %t.o
 ; RUN: obj2yaml %t.separate.wasm | FileCheck %s --check-prefix=SEPARATE
 
 ; SEPARATE-NOT:                  DATACOUNT
 ; SEPARATE-LABEL: - Type:            DATA
 ; SEPARATE-NEXT:    Segments:
 ; SEPARATE-NEXT:      - SectionOffset:   7

 ; SEPARATE-NEXT:  - Type:            CUSTOM
 ; SEPARATE-NEXT:    Name:            name
 ; SEPARATE-NEXT:    FunctionNames:
 ; SEPARATE-NEXT:      - Index:           0
 ; SEPARATE-NEXT:        Name:            __wasm_call_ctors
 ; SEPARATE-NEXT:    GlobalNames:
 ; SEPARATE-NEXT:      - Index:           0
 ; SEPARATE-NEXT:        Name:            __stack_pointer
-; SEPARATE-NOT:       - Index:
+; SEPARATE-NEXT:    DataSegmentNames:
+; SEPARATE-NEXT:      - Index:           0
+; SEPARATE-NEXT:        Name:            .rodata
 
 ; RUN: wasm-ld -no-gc-sections --no-entry --shared-memory --max-memory=131072 -o %t.merged.passive.wasm %t.passive.o
 ; RUN: obj2yaml %t.merged.passive.wasm | FileCheck %s --check-prefix=PASSIVE-MERGE
 ; RUN: wasm-ld -mwasm64 -no-gc-sections --no-entry --shared-memory --max-memory=131072 -o %t.merged.passive64.wasm %t.passive64.o
 ; RUN: obj2yaml %t.merged.passive64.wasm | FileCheck %s --check-prefix=PASSIVE-MERGE
 
 ; PASSIVE-MERGE-LABEL: - Type:            DATACOUNT
 ; PASSIVE-MERGE-NEXT:    Count:           2

lld/test/wasm/gc-sections.ll

 ; CHECK-NEXT:         Name:            _start
 ; CHECK-NEXT:       - Index:           2
 ; CHECK-NEXT:         Name:            use_global
 ; CHECK-NEXT:     GlobalNames:
 ; CHECK-NEXT:       - Index:           0
 ; CHECK-NEXT:         Name:            __stack_pointer
 ; CHECK-NEXT:       - Index:           1
 ; CHECK-NEXT:         Name:            used_global
+; CHECK-NEXT:     DataSegmentNames:
+; CHECK-NEXT:       - Index:           0
+; CHECK-NEXT:         Name:            .data
 ; CHECK-NEXT: ...
 
 ; RUN: wasm-ld -print-gc-sections --no-gc-sections -o %t1.no-gc.wasm \
 ; RUN:     %t.o %t_globals.o
 ; RUN: obj2yaml %t1.no-gc.wasm | FileCheck %s -check-prefix=NO-GC
 
 ; NO-GC:        - Type:            TYPE
 ; NO-GC-NEXT:     Signatures:

 ; NO-GC-NEXT:         Name:            use_global
 ; NO-GC-NEXT:     GlobalNames:
 ; NO-GC-NEXT:       - Index:           0
 ; NO-GC-NEXT:         Name:            __stack_pointer
 ; NO-GC-NEXT:       - Index:           1
 ; NO-GC-NEXT:         Name:            unused_global
 ; NO-GC-NEXT:       - Index:           2
 ; NO-GC-NEXT:         Name:            used_global
+; NO-GC-NEXT:     DataSegmentNames:
+; NO-GC-NEXT:       - Index:           0
+; NO-GC-NEXT:         Name:            .data
 ; NO-GC-NEXT: ...
 
 ; RUN: not wasm-ld --gc-sections --relocatable -o %t1.no-gc.wasm %t.o 2>&1 | FileCheck %s -check-prefix=CHECK-ERROR
 ; CHECK-ERROR: error: -r and --gc-sections may not be used together

lld/test/wasm/local-symbols.ll

 ; CHECK-NEXT:     FunctionNames:
 ; CHECK-NEXT:       - Index:           0
 ; CHECK-NEXT:         Name:            baz
 ; CHECK-NEXT:       - Index:           1
 ; CHECK-NEXT:         Name:            _start
 ; CHECK-NEXT:     GlobalNames:
 ; CHECK-NEXT:       - Index:           0
 ; CHECK-NEXT:         Name:            __stack_pointer
+; CHECK-NEXT:     DataSegmentNames:
+; CHECK-NEXT:       - Index:           0
+; CHECK-NEXT:         Name:            .data
 ; CHECK-NEXT: ...

lld/test/wasm/locals-duplicate.test

 ; CHECK-NEXT:         Name:            get_func1B
 ; CHECK-NEXT:       - Index:           16
 ; CHECK-NEXT:         Name:            get_func2B
 ; CHECK-NEXT:       - Index:           17
 ; CHECK-NEXT:         Name:            get_func3B
 ; CHECK-NEXT:     GlobalNames:
 ; CHECK-NEXT:       - Index:           0
 ; CHECK-NEXT:         Name:            __stack_pointer
+; CHECK-NEXT:     DataSegmentNames:
+; CHECK-NEXT:       - Index:           0
+; CHECK-NEXT:         Name:            .data
 ; CHECK-NEXT: ...
 
 
 ; RUN: wasm-ld -r --no-entry -o %t.reloc.wasm %t1.o %t2.o
 ; RUN: obj2yaml %t.reloc.wasm | FileCheck -check-prefix=RELOC %s
 
 ; RELOC:      --- !WASM
 ; RELOC-NEXT: FileHeader:

 ; RELOC-NEXT:       - Index:           14
 ; RELOC-NEXT:         Name:            get_global3B
 ; RELOC-NEXT:       - Index:           15
 ; RELOC-NEXT:         Name:            get_func1B
 ; RELOC-NEXT:       - Index:           16
 ; RELOC-NEXT:         Name:            get_func2B
 ; RELOC-NEXT:       - Index:           17
 ; RELOC-NEXT:         Name:            get_func3B
+; RELOC-NEXT:     DataSegmentNames:
+; RELOC-NEXT:       - Index:           0
+; RELOC-NEXT:         Name:            .data.colliding_global1
+; RELOC-NEXT:       - Index:           1
+; RELOC-NEXT:         Name:            .data.colliding_global2
+; RELOC-NEXT:       - Index:           2
+; RELOC-NEXT:         Name:            .data.colliding_global3
 ; RELOC-NEXT: ...

lld/test/wasm/map-file.s

 # CHECK-NEXT:       -       3f        9                 bar
 # CHECK-NEXT:       -       48        9         {{.*}}{{/|\\}}map-file.s.tmp1.o:(_start)
 # CHECK-NEXT:       -       48        9                 _start
 # CHECK-NEXT:       -       53        d DATA
 # CHECK-NEXT:     400       54        4 .data
 # CHECK-NEXT:     400       5a        4         {{.*}}{{/|\\}}map-file.s.tmp1.o:(.data.somedata)
 # CHECK-NEXT:     400       5a        4                 somedata
 # CHECK-NEXT:       -       60       12 CUSTOM(.debug_info)
-# CHECK-NEXT:       -       72       2b CUSTOM(name)
+# CHECK-NEXT:       -       72       35 CUSTOM(name)
 
 # RUN: not wasm-ld %t1.o -o /dev/null -Map=/ 2>&1 \
 # RUN:  | FileCheck -check-prefix=FAIL %s
 # FAIL: wasm-ld: error: cannot open map file /

lld/test/wasm/signature-mismatch.ll

 ; YAML-NEXT:         Name:            _start
 ; YAML-NEXT:       - Index:           2
 ; YAML-NEXT:         Name:            ret32
 ; YAML-NEXT:       - Index:           3
 ; YAML-NEXT:         Name:            call_ret32
 ; YAML-NEXT:     GlobalNames:
 ; YAML-NEXT:       - Index:           0
 ; YAML-NEXT:         Name:            __stack_pointer
+; YAML-NEXT:     DataSegmentNames:
+; YAML-NEXT:       - Index:           0
+; YAML-NEXT:         Name:            .data
 ; YAML-NEXT: ...
 
 ;      RELOC:     Name:            linking
 ; RELOC-NEXT:     Version:         2
 ; RELOC-NEXT:     SymbolTable:
 ; RELOC-NEXT:       - Index:           0
 ; RELOC-NEXT:         Kind:            FUNCTION
 ; RELOC-NEXT:         Name:            _start

lld/test/wasm/weak-symbols.s

 # CHECK-NEXT:         Name:            weakFn
 # CHECK-NEXT:       - Index:           2
 # CHECK-NEXT:         Name:            exportWeak1
 # CHECK-NEXT:       - Index:           3
 # CHECK-NEXT:         Name:            exportWeak2
 # CHECK-NEXT:     GlobalNames:
 # CHECK-NEXT:       - Index:           0
 # CHECK-NEXT:         Name:            __stack_pointer
+# CHECK-NEXT:     DataSegmentNames:
+# CHECK-NEXT:       - Index:           0
+# CHECK-NEXT:         Name:            .data
 # CHECK-NEXT: ...

lld/wasm/SyntheticSections.h

protected:
   llvm::StringMap<uint32_t> sectionSymbolIndices;
   const std::vector<WasmInitEntry> &initFunctions;
   const std::vector<OutputSegment *> &dataSegments;
 };
 
 // Create the custom "name" section containing debug symbol names.
 class NameSection : public SyntheticSection {
 public:
-  NameSection() : SyntheticSection(llvm::wasm::WASM_SEC_CUSTOM, "name") {}
+  NameSection(ArrayRef<OutputSegment *> segments)
+      : SyntheticSection(llvm::wasm::WASM_SEC_CUSTOM, "name"),
+        segments(segments) {}
   bool isNeeded() const override {
     return !config->stripDebug && !config->stripAll && numNames() > 0;
   }
   void writeBody() override;
   unsigned numNames() const { return numNamedGlobals() + numNamedFunctions(); }
   unsigned numNamedGlobals() const;
   unsigned numNamedFunctions() const;
+  unsigned numNamedDataSegments() const;
+
+protected:
+  ArrayRef<OutputSegment *> segments;
 };
 
 class ProducersSection : public SyntheticSection {
 public:
   ProducersSection()
       : SyntheticSection(llvm::wasm::WASM_SEC_CUSTOM, "producers") {}
   bool isNeeded() const override {
     return !config->stripAll && fieldCount() > 0;

lld/wasm/SyntheticSections.cpp

unsigned NameSection::numNamedGlobals() const {
   for (const InputGlobal *g : out.globalSec->inputGlobals)
     if (!g->getName().empty())
       ++numNames;
 
   numNames += out.globalSec->internalGotSymbols.size();
   return numNames;
 }
 
+unsigned NameSection::numNamedDataSegments() const {
+  unsigned numNames = 0;
+
+  for (const OutputSegment *s : segments)
+    if (!s->name.empty())
+      ++numNames;
+
+  return numNames;
+}
+
 // Create the custom "name" section containing debug symbol names.
 void NameSection::writeBody() {
   unsigned count = numNamedFunctions();
   if (count) {
     SubSection sub(WASM_NAMES_FUNCTION);
     writeUleb128(sub.os, count, "name count");
 
     // Function names appear in function index order.  As it happens
if (count) {
     }
     for (Symbol *s : out.globalSec->internalGotSymbols) {
       writeUleb128(sub.os, s->getGOTIndex(), "global index");
       writeStr(sub.os, toString(*s), "symbol name");
     }
 
     sub.writeTo(bodyOutputStream);
   }
+
+  count = numNamedDataSegments();
+  if (count) {
+    SubSection sub(WASM_NAMES_DATA_SEGMENT);
+    writeUleb128(sub.os, count, "name count");
+
+    for (OutputSegment *s : segments) {
+      writeUleb128(sub.os, s->index, "global index");
+      writeStr(sub.os, s->name, "segment name");
+    }
+
+    sub.writeTo(bodyOutputStream);
+  }
 }
 
 void ProducersSection::addInfo(const WasmProducerInfo &info) {
   for (auto &producers :
        {std::make_pair(&info.Languages, &languages),
         std::make_pair(&info.Tools, &tools), std::make_pair(&info.SDKs, &sDKs)})
     for (auto &producer : *producers.first)
       if (producers.second->end() ==

lld/wasm/Writer.cpp

void Writer::createSyntheticSections() {
   out.memorySec = make<MemorySection>();
   out.eventSec = make<EventSection>();
   out.globalSec = make<GlobalSection>();
   out.exportSec = make<ExportSection>();
   out.startSec = make<StartSection>(hasPassiveInitializedSegments());
   out.elemSec = make<ElemSection>();
   out.dataCountSec = make<DataCountSection>(segments);
   out.linkingSec = make<LinkingSection>(initFunctions, segments);
-  out.nameSec = make<NameSection>();
+  out.nameSec = make<NameSection>(segments);
   out.producersSec = make<ProducersSection>();
   out.targetFeaturesSec = make<TargetFeaturesSection>();
 }
 
 void Writer::run() {
   if (config->relocatable || config->isPic)
     config->globalBase = 0;
 

llvm/include/llvm/BinaryFormat/Wasm.h

union {
     uint32_t ElementIndex;
     // For a data symbols, the address of the data relative to segment.
     WasmDataReference DataRef;
   };
 };
 
 enum class NameType {
   FUNCTION,
-  GLOBAL
+  GLOBAL,
+  DATA_SEGMENT,
 };
 
 struct WasmDebugName {
   NameType Type;
   uint32_t Index;
   StringRef Name;
 };
 

 enum : uint8_t {
   WASM_FEATURE_PREFIX_USED = '+',
   WASM_FEATURE_PREFIX_REQUIRED = '=',
   WASM_FEATURE_PREFIX_DISALLOWED = '-',
 };
 
 // Kind codes used in the custom "name" section
 enum : unsigned {
-  WASM_NAMES_FUNCTION = 0x1,
-  WASM_NAMES_LOCAL = 0x2,
-  WASM_NAMES_GLOBAL = 0x7,
+  WASM_NAMES_FUNCTION = 1,
+  WASM_NAMES_LOCAL = 2,
+  WASM_NAMES_GLOBAL = 7,
+  WASM_NAMES_DATA_SEGMENT = 9,
 };
 
 // Kind codes used in the custom "linking" section
 enum : unsigned {
   WASM_SEGMENT_INFO = 0x5,
   WASM_INIT_FUNCS = 0x6,
   WASM_COMDAT_INFO = 0x7,
   WASM_SYMBOL_TABLE = 0x8,

llvm/include/llvm/ObjectYAML/WasmYAML.h

struct NameSection : CustomSection {
 
   static bool classof(const Section *S) {
     auto C = dyn_cast<CustomSection>(S);
     return C && C->Name == "name";
   }
 
   std::vector<NameEntry> FunctionNames;
   std::vector<NameEntry> GlobalNames;
+  std::vector<NameEntry> DataSegmentNames;
 };
 
 struct LinkingSection : CustomSection {
   LinkingSection() : CustomSection("linking") {}
 
   static bool classof(const Section *S) {
     auto C = dyn_cast<CustomSection>(S);
     return C && C->Name == "linking";

llvm/lib/Object/WasmObjectFile.cpp

if (Ctx.Ptr != Ctx.End)
     return make_error<GenericBinaryError>("dylink section ended prematurely",
                                           object_error::parse_failed);
   return Error::success();
 }
 
 Error WasmObjectFile::parseNameSection(ReadContext &Ctx) {
   llvm::DenseSet<uint64_t> SeenFunctions;
   llvm::DenseSet<uint64_t> SeenGlobals;
+  llvm::DenseSet<uint64_t> SeenSegments;
   if (FunctionTypes.size() && !SeenCodeSection) {
     return make_error<GenericBinaryError>("Names must come after code section",
                                           object_error::parse_failed);
   }
 
   while (Ctx.Ptr < Ctx.End) {
     uint8_t Type = readUint8(Ctx);
     uint32_t Size = readVaruint32(Ctx);
     const uint8_t *SubSectionEnd = Ctx.Ptr + Size;
     switch (Type) {
     case wasm::WASM_NAMES_FUNCTION:
-    case wasm::WASM_NAMES_GLOBAL: {
+    case wasm::WASM_NAMES_GLOBAL:
+    case wasm::WASM_NAMES_DATA_SEGMENT: {
       uint32_t Count = readVaruint32(Ctx);
       while (Count--) {
         uint32_t Index = readVaruint32(Ctx);
         StringRef Name = readString(Ctx);
+        wasm::NameType nameType = wasm::NameType::FUNCTION;
         if (Type == wasm::WASM_NAMES_FUNCTION) {
           if (!SeenFunctions.insert(Index).second)
             return make_error<GenericBinaryError>(
                 "Function named more than once", object_error::parse_failed);
           if (!isValidFunctionIndex(Index) || Name.empty())
             return make_error<GenericBinaryError>("Invalid name entry",
                                                   object_error::parse_failed);
 
           if (isDefinedFunctionIndex(Index))
             getDefinedFunction(Index).DebugName = Name;
-        } else {
+        } else if (Type == wasm::WASM_NAMES_GLOBAL) {
+          nameType = wasm::NameType::GLOBAL;
           if (!SeenGlobals.insert(Index).second)
             return make_error<GenericBinaryError>("Global named more than once",
                                                   object_error::parse_failed);
           if (!isValidGlobalIndex(Index) || Name.empty())
             return make_error<GenericBinaryError>("Invalid name entry",
                                                   object_error::parse_failed);
+        } else {
+          nameType = wasm::NameType::DATA_SEGMENT;
+          if (!SeenSegments.insert(Index).second)
+            return make_error<GenericBinaryError>(
+                "Segment named more than once", object_error::parse_failed);
+          if (Index > DataSegments.size())
+            return make_error<GenericBinaryError>("Invalid named data segment",
+                                                  object_error::parse_failed);
         }
-        wasm::NameType T = Type == wasm::WASM_NAMES_FUNCTION
-                               ? wasm::NameType::FUNCTION
-                               : wasm::NameType::GLOBAL;
-        DebugNames.push_back(wasm::WasmDebugName{T, Index, Name});
+        DebugNames.push_back(wasm::WasmDebugName{nameType, Index, Name});
       }
       break;
     }
     // Ignore local names for now
     case wasm::WASM_NAMES_LOCAL:
     default:
       Ctx.Ptr += Size;
       break;

llvm/lib/ObjectYAML/WasmEmitter.cpp

if (Section.GlobalNames.size()) {
     encodeULEB128(Section.GlobalNames.size(), SubSection.getStream());
     for (const WasmYAML::NameEntry &NameEntry : Section.GlobalNames) {
       encodeULEB128(NameEntry.Index, SubSection.getStream());
       writeStringRef(NameEntry.Name, SubSection.getStream());
     }
 
     SubSection.done();
   }
+  if (Section.DataSegmentNames.size()) {
+    writeUint8(OS, wasm::WASM_NAMES_DATA_SEGMENT);
+
+    SubSectionWriter SubSection(OS);
+
+    encodeULEB128(Section.DataSegmentNames.size(), SubSection.getStream());
+    for (const WasmYAML::NameEntry &NameEntry : Section.DataSegmentNames) {
+      encodeULEB128(NameEntry.Index, SubSection.getStream());
+      writeStringRef(NameEntry.Name, SubSection.getStream());
+    }
+
+    SubSection.done();
+  }
 }
 
 void WasmWriter::writeSectionContent(raw_ostream &OS,
                                      WasmYAML::ProducersSection &Section) {
   writeStringRef(Section.Name, OS);
   int Fields = int(!Section.Languages.empty()) + int(!Section.Tools.empty()) +
                int(!Section.SDKs.empty());
   if (Fields == 0)

llvm/lib/ObjectYAML/WasmYAML.cpp

static void sectionMapping(IO &IO, WasmYAML::DylinkSection &Section) {
   IO.mapRequired("Needed", Section.Needed);
 }
 
 static void sectionMapping(IO &IO, WasmYAML::NameSection &Section) {
   commonSectionMapping(IO, Section);
   IO.mapRequired("Name", Section.Name);
   IO.mapOptional("FunctionNames", Section.FunctionNames);
   IO.mapOptional("GlobalNames", Section.GlobalNames);
+  IO.mapOptional("DataSegmentNames", Section.DataSegmentNames);
 }
 
 static void sectionMapping(IO &IO, WasmYAML::LinkingSection &Section) {
   commonSectionMapping(IO, Section);
   IO.mapRequired("Name", Section.Name);
   IO.mapRequired("Version", Section.Version);
   IO.mapOptional("SymbolTable", Section.SymbolTable);
   IO.mapOptional("SegmentInfo", Section.SegmentInfos);

llvm/tools/obj2yaml/wasm2yaml.cpp

if (WasmSec.Name == "dylink") {
     std::unique_ptr<WasmYAML::NameSection> NameSec =
         std::make_unique<WasmYAML::NameSection>();
     for (const llvm::wasm::WasmDebugName &Name : Obj.debugNames()) {
       WasmYAML::NameEntry NameEntry;
       NameEntry.Name = Name.Name;
       NameEntry.Index = Name.Index;
       if (Name.Type == llvm::wasm::NameType::FUNCTION) {
         NameSec->FunctionNames.push_back(NameEntry);
-      } else {
-        assert(Name.Type == llvm::wasm::NameType::GLOBAL);
+      } else if (Name.Type == llvm::wasm::NameType::GLOBAL) {
         NameSec->GlobalNames.push_back(NameEntry);
+      } else {
+        assert(Name.Type == llvm::wasm::NameType::DATA_SEGMENT);
+        NameSec->DataSegmentNames.push_back(NameEntry);
       }
     }
     CustomSec = std::move(NameSec);
   } else if (WasmSec.Name == "linking") {
     std::unique_ptr<WasmYAML::LinkingSection> LinkingSec =
         std::make_unique<WasmYAML::LinkingSection>();
     LinkingSec->Version = Obj.linkingData().Version;