[lld][WebAssembly] Split __wasm_apply_relocs function in two

[sbc100]

Summary

We have two types of relocations that we apply on startup:

1. Relocations that apply to wasm globals
2. Relocations that apply to wasm memory

The first set of relocations use only the __memory_base import to
update a set of internal globals. Because wasm globals are thread local
these need to run on each thread. Memory relocations, like static
constructors, must only be run once.

To ensure global relocations run on all threads and because the only
depend on the immutable __memory_base import we can run them during
the WebAssembly start functions, instead of waiting until the
post-instantiation __wasm_call_ctors.

[sbc100]

revert

[tlively]

Looks good! Can you add a test that uses __wasm_start?

lld/wasm/Writer.cpp

891–893

[sbc100]

• feedback

[sbc100]

Added a test. Once again I wish we had a good disassembler to make the test more readable.

[tlively]

Nice!

lld/wasm/Writer.cpp

891

Still has an extra "a" in "create a synthetic functions" :)

lld/test/wasm/bsymbolic.s

 // RUN: llvm-mc -filetype=obj -triple=wasm32-unknown-unknown %s -o %t.o
-// RUN: wasm-ld --no-entry -Bsymbolic %t.o -o %t2.so 2>&1 | FileCheck -check-prefix=WARNING %s
+// RUN: wasm-ld --no-entry -Bsymbolic %t.o -o %t.wasm 2>&1 | FileCheck -check-prefix=WARNING %s
 // WARNING: warning: -Bsymbolic is only meaningful when combined with -shared
 
 // RUN: wasm-ld --experimental-pic -shared %t.o -o %t0.so
 // RUN: obj2yaml %t0.so | FileCheck -check-prefix=NOOPTION %s
 
 // RUN: wasm-ld --experimental-pic -shared -Bsymbolic %t.o -o %t1.so
 // RUN: obj2yaml %t1.so | FileCheck -check-prefix=SYMBOLIC %s
 

lld/test/wasm/data-segments.ll

 ; PASSIVE-NEXT:      - Index:           0
 ; PASSIVE-NEXT:        Name:            __wasm_call_ctors
 ; PASSIVE-NEXT:      - Index:           1
 ; PASSIVE-NEXT:        Name:            __wasm_init_tls
 ; PASSIVE-NEXT:      - Index:           2
 ; PASSIVE-NEXT:        Name:            __wasm_init_memory
 
 ;      PASSIVE-PIC:  - Type:            START
-; PASSIVE-PIC-NEXT:    StartFunction:   3
+; PASSIVE-PIC-NEXT:    StartFunction:   2
 ; PASSIVE-PIC-NEXT:  - Type:            DATACOUNT
 ; PASSIVE-PIC-NEXT:    Count:           1
 ; PASSIVE-PIC-NEXT:  - Type:            CODE
 ; PASSIVE-PIC-NEXT:    Functions:
 ; PASSIVE-PIC-NEXT:      - Index:           0
 ; PASSIVE-PIC-NEXT:        Locals:          []
-; PASSIVE-PIC-NEXT:        Body:            10010B
+; PASSIVE-PIC-NEXT:        Body:            10030B
 ; PASSIVE-PIC-NEXT:      - Index:           1
 ; PASSIVE-PIC-NEXT:        Locals:          []
 ; PASSIVE-PIC-NEXT:        Body:            0B
 ; PASSIVE-PIC-NEXT:      - Index:           2
-; PASSIVE-PIC-NEXT:        Locals:          []
-; PASSIVE-PIC-NEXT:        Body:            0B
-; PASSIVE-PIC-NEXT:      - Index:           3
 ; PASSIVE-PIC-NEXT:        Locals:
 ; PASSIVE32-PIC-NEXT:          - Type:            I32
 ; PASSIVE64-PIC-NEXT:          - Type:            I64
 ; PASSIVE-PIC-NEXT:            Count:           1
 ; PASSIVE32-PIC-NEXT:        Body:            230141B4CE006A2100200041004101FE480200044020004101427FFE0102001A05410023016A410041B1CE00FC08000020004102FE1702002000417FFE0002001A0BFC09000B
 ; PASSIVE64-PIC-NEXT:        Body:            230142B4CE006A2100200041004101FE480200044020004101427FFE0102001A05420023016A410041B1CE00FC08000020004102FE1702002000417FFE0002001A0BFC09000B
+; PASSIVE-PIC-NEXT:      - Index:           3
+; PASSIVE-PIC-NEXT:        Locals:          []
+; PASSIVE-PIC-NEXT:        Body:            0B
 ; PASSIVE-PIC-NEXT:  - Type:            DATA
 ; PASSIVE-PIC-NEXT:    Segments:
 ; PASSIVE-PIC-NEXT:      - SectionOffset:   4
 ; PASSIVE-PIC-NEXT:        InitFlags:       1
 
 ;      PASSIVE-PIC:  - Type:            CUSTOM
 ; PASSIVE-PIC-NEXT:    Name:            name
 ; PASSIVE-PIC-NEXT:    FunctionNames:
 ; PASSIVE-PIC-NEXT:      - Index:           0
 ; PASSIVE-PIC-NEXT:        Name:            __wasm_call_ctors
 ; PASSIVE-PIC-NEXT:      - Index:           1
-; PASSIVE-PIC-NEXT:        Name:            __wasm_apply_relocs
-; PASSIVE-PIC-NEXT:      - Index:           2
 ; PASSIVE-PIC-NEXT:        Name:            __wasm_init_tls
-; PASSIVE-PIC-NEXT:      - Index:           3
+; PASSIVE-PIC-NEXT:      - Index:           2
 ; PASSIVE-PIC-NEXT:        Name:            __wasm_init_memory
+; PASSIVE-PIC-NEXT:      - Index:           3
+; PASSIVE-PIC-NEXT:        Name:            __wasm_apply_data_relocs

lld/test/wasm/pie.ll

 ; RUN: llc -relocation-model=pic -mattr=+mutable-globals -filetype=obj %s -o %t.o
 ; RUN: wasm-ld --no-gc-sections --allow-undefined --experimental-pic -pie -o %t.wasm %t.o
-; RUN: obj2yaml %t.wasm | FileCheck %s
 
 target triple = "wasm32-unknown-emscripten"
 
 @data = global i32 2, align 4
 @data_external = external global i32
 @indirect_func = local_unnamed_addr global i32 ()* @foo, align 4
 
 @data_addr = local_unnamed_addr global i32* @data, align 4

 ; CHECK-NEXT:         GlobalType:      I32
 ; CHECK-NEXT:         GlobalMutable:   false
 ; CHECK-NEXT:       - Module:          env
 ; CHECK-NEXT:         Field:           __table_base
 ; CHECK-NEXT:         Kind:            GLOBAL
 ; CHECK-NEXT:         GlobalType:      I32
 ; CHECK-NEXT:         GlobalMutable:   false
 
+; CHECK:        - Type:            START
+; CHECK-NEXT:     StartFunction:   2
+
+; CHECK:        - Type:            CUSTOM
+; CHECK-NEXT:     Name:            name
+; CHECK-NEXT:     FunctionNames:
+; CHECK-NEXT:       - Index:           0
+; CHECK-NEXT:         Name:            __wasm_call_ctors
+; CHECK-NEXT:       - Index:           1
+; CHECK-NEXT:         Name:            __wasm_apply_data_relocs
+; CHECK-NEXT:       - Index:           2
+; CHECK-NEXT:         Name:            __wasm_apply_global_relocs
+
+
+; Run the same test with threading support.  In this mode
+; we expect __wasm_init_memory and __wasm_apply_data_relocs
+; to be generated along with __wasm_start as the start
+; function.
+
+; RUN: llc -relocation-model=pic -mattr=+mutable-globals,+atomics,+bulk-memory -filetype=obj %s -o %t.shmem.o
+; RUN: wasm-ld --no-gc-sections --shared-memory --allow-undefined --experimental-pic -pie -o %t.shmem.wasm %t.shmem.o
+; RUN: obj2yaml %t.shmem.wasm | FileCheck %s --check-prefix=SHMEM
+
+; SHMEM:         - Type:            CODE
+; SHMEM:           - Index:           5
+; SHMEM-NEXT:        Locals:          []
+; SHMEM-NEXT:        Body:            100210040B
+
+; SHMEM:         FunctionNames:
+; SHMEM-NEXT:      - Index:           0
+; SHMEM-NEXT:        Name:            __wasm_call_ctors
+; SHMEM-NEXT:      - Index:           1
+; SHMEM-NEXT:        Name:            __wasm_init_tls
+; SHMEM-NEXT:      - Index:           2
+; SHMEM-NEXT:        Name:            __wasm_init_memory
+; SHMEM-NEXT:      - Index:           3
+; SHMEM-NEXT:        Name:            __wasm_apply_data_relocs
+; SHMEM-NEXT:      - Index:           4
+; SHMEM-NEXT:        Name:            __wasm_apply_global_relocs
+; SHMEM-NEXT:      - Index:           5
+; SHMEM-NEXT:        Name:            __wasm_start
+; SHMEM-NEXT:      - Index:           6
+; SHMEM-NEXT:        Name:            foo
+; SHMEM-NEXT:      - Index:           7
+; SHMEM-NEXT:        Name:            get_data_address
+; SHMEM-NEXT:      - Index:           8
+; SHMEM-NEXT:        Name:            _start
 

lld/test/wasm/weak-undefined-pic.s

 # CHECK-NEXT:      - Index:           1
 # CHECK-NEXT:        Name:            get_foo_addr
 # CHECK-NEXT:      - Index:           2
 # CHECK-NEXT:        Name:            _start
 # CHECK-NEXT:    GlobalNames:
 # CHECK-NEXT:      - Index:           0
 # CHECK-NEXT:        Name:            __stack_pointer
 # CHECK-NEXT:      - Index:           1
-# CHECK-NEXT:        Name:            'undefined_weak:foo'
+# CHECK-NEXT:        Name:            'GOT.func.internal.undefined_weak:foo'
 
 # With `-pie` or `-shared` the resolution should be deferred to the dynamic
 # linker and the function address should be imported as GOT.func.foo.
 #
 # RUN: wasm-ld --experimental-pic -pie %t.o -o %t3.wasm
 # RUN: obj2yaml %t3.wasm | FileCheck %s --check-prefix=IMPORT
 
 #      IMPORT:  - Type:            IMPORT

lld/wasm/Driver.cpp

static llvm::wasm::WasmGlobalType mutableGlobalTypeI32 = {WASM_TYPE_I32,
                                                             true};
   static llvm::wasm::WasmGlobalType mutableGlobalTypeI64 = {WASM_TYPE_I64,
                                                             true};
   WasmSym::callCtors = symtab->addSyntheticFunction(
       "__wasm_call_ctors", WASM_SYMBOL_VISIBILITY_HIDDEN,
       make<SyntheticFunction>(nullSignature, "__wasm_call_ctors"));
 
   if (config->isPic) {
-    // For PIC code we create a synthetic function __wasm_apply_relocs which
-    // is called from __wasm_call_ctors before the user-level constructors.
-    WasmSym::applyRelocs = symtab->addSyntheticFunction(
-        "__wasm_apply_relocs", WASM_SYMBOL_VISIBILITY_HIDDEN,
-        make<SyntheticFunction>(nullSignature, "__wasm_apply_relocs"));
-  }
-
-  if (config->isPic) {
     WasmSym::stackPointer =
         createUndefinedGlobal("__stack_pointer", config->is64.getValueOr(false)
                                                      ? &mutableGlobalTypeI64
                                                      : &mutableGlobalTypeI32);
     // For PIC code, we import two global variables (__memory_base and
     // __table_base) from the environment and use these as the offset at
     // which to load our static data and function table.
     // See:

lld/wasm/MarkLive.cpp

void MarkLive::run() {
   // We need to preserve any no-strip or exported symbol
   for (Symbol *sym : symtab->getSymbols())
     if (sym->isNoStrip() || sym->isExported())
       enqueue(sym);
 
   if (WasmSym::callDtors)
     enqueue(WasmSym::callDtors);
 
-  if (WasmSym::applyRelocs)
-    enqueue(WasmSym::applyRelocs);
-
   // Enqueue constructors in objects explicitly live from the command-line.
   for (const ObjFile *obj : symtab->objectFiles)
     if (obj->isLive())
       enqueueInitFunctions(obj);
 
   mark();
 
   // If we have any non-discarded init functions, mark `__wasm_call_ctors` as

lld/wasm/Symbols.h

struct WasmSym {
   // __wasm_call_ctors
   // Function that directly calls all ctors in priority order.
   static DefinedFunction *callCtors;
 
   // __wasm_call_dtors
   // Function that calls the libc/etc. cleanup function.
   static DefinedFunction *callDtors;
 
-  // __wasm_apply_relocs
+  // __wasm_apply_data_relocs
   // Function that applies relocations to data segment post-instantiation.
-  static DefinedFunction *applyRelocs;
+  static DefinedFunction *applyDataRelocs;
+
+  // __wasm_apply_global_relocs
+  // Function that applies relocations to data segment post-instantiation.
+  // Unlike __wasm_apply_data_relocs this needs to run on every thread.
+  static DefinedFunction *applyGlobalRelocs;
 
   // __wasm_init_tls
   // Function that allocates thread-local storage and initializes it.
   static DefinedFunction *initTLS;
 
+  // Pointer to the function that is to be used in the start section.
+  // (normally an alias of initMemory, or applyGlobalRelocs).
+  static DefinedFunction *startFunction;
+
   // __dso_handle
   // Symbol used in calls to __cxa_atexit to determine current DLL
   static DefinedData *dsoHandle;
 
   // __table_base
   // Used in PIC code for offset of indirect function table
   static UndefinedGlobal *tableBase;
   static DefinedData *definedTableBase;

lld/wasm/Symbols.cpp

std::string toString(wasm::Symbol::Kind kind) {
   }
   llvm_unreachable("invalid symbol kind");
 }
 
 namespace wasm {
 DefinedFunction *WasmSym::callCtors;
 DefinedFunction *WasmSym::callDtors;
 DefinedFunction *WasmSym::initMemory;
-DefinedFunction *WasmSym::applyRelocs;
+DefinedFunction *WasmSym::applyDataRelocs;
+DefinedFunction *WasmSym::applyGlobalRelocs;
 DefinedFunction *WasmSym::initTLS;
+DefinedFunction *WasmSym::startFunction;
 DefinedData *WasmSym::dsoHandle;
 DefinedData *WasmSym::dataEnd;
 DefinedData *WasmSym::globalBase;
 DefinedData *WasmSym::heapBase;
 DefinedData *WasmSym::initMemoryFlag;
 GlobalSymbol *WasmSym::stackPointer;
 GlobalSymbol *WasmSym::tlsBase;
 GlobalSymbol *WasmSym::tlsSize;

lld/wasm/SyntheticSections.h

public:
   //
   // For the static linking case these internal globals can be completely
   // eliminated by a post-link optimizer such as wasm-opt.
   //
   // TODO(sbc): Another approach to optimizing these away could be to use
   // specific relocation types combined with linker relaxation which could
   // transform a `global.get` to an `i32.const`.
   void addInternalGOTEntry(Symbol *sym);
+  bool needsRelocations() { return internalGotSymbols.size(); }
   void generateRelocationCode(raw_ostream &os) const;
 
   std::vector<const DefinedData *> dataAddressGlobals;
   std::vector<InputGlobal *> inputGlobals;
   std::vector<Symbol *> internalGotSymbols;
 
 protected:
   bool isSealed = false;

lld/wasm/SyntheticSections.cpp

void ExportSection::writeBody() {
   raw_ostream &os = bodyOutputStream;
 
   writeUleb128(os, exports.size(), "export count");
   for (const WasmExport &export_ : exports)
     writeExport(os, export_);
 }
 
 bool StartSection::isNeeded() const {
-  return WasmSym::initMemory != nullptr;
+  return WasmSym::startFunction != nullptr;
 }
 
 void StartSection::writeBody() {
   raw_ostream &os = bodyOutputStream;
-  writeUleb128(os, WasmSym::initMemory->getFunctionIndex(), "function index");
+  writeUleb128(os, WasmSym::startFunction->getFunctionIndex(),
+               "function index");
 }
 
 void ElemSection::addEntry(FunctionSymbol *sym) {
   // Don't add stub functions to the wasm table.  The address of all stub
   // functions should be zero and they should they don't appear in the table.
   // They only exist so that the calls to missing functions can validate.
   if (sym->hasTableIndex() || sym->isStub)
     return;
if (count) {
     for (const InputGlobal *g : out.globalSec->inputGlobals) {
       if (!g->getName().empty()) {
         writeUleb128(sub.os, g->getGlobalIndex(), "global index");
         writeStr(sub.os, maybeDemangleSymbol(g->getName()), "symbol name");
       }
     }
     for (Symbol *s : out.globalSec->internalGotSymbols) {
       writeUleb128(sub.os, s->getGOTIndex(), "global index");
-      writeStr(sub.os, toString(*s), "symbol name");
+      if (isa<FunctionSymbol>(s))
+        writeStr(sub.os, "GOT.func.internal." + toString(*s), "symbol name");
+      else
+        writeStr(sub.os, "GOT.data.internal." + toString(*s), "symbol name");
     }
 
     sub.writeTo(bodyOutputStream);
   }
 
   count = numNamedDataSegments();
   if (count) {
     SubSection sub(WASM_NAMES_DATA_SEGMENT);

lld/wasm/Writer.cpp

 private:
   void openFile();
 
   bool needsPassiveInitialization(const OutputSegment *segment);
   bool hasPassiveInitializedSegments();
 
   void createSyntheticInitFunctions();
   void createInitMemoryFunction();
-  void createApplyRelocationsFunction();
+  void createStartFunction();
+  void createApplyDataRelocationsFunction();
+  void createApplyGlobalRelocationsFunction();
   void createCallCtorsFunction();
   void createInitTLSFunction();
   void createCommandExportWrappers();
   void createCommandExportWrapper(uint32_t functionIndex, DefinedFunction *f);
 
   void assignIndexes();
   void populateSymtab();
   void populateProducers();
if (seg->name == ".tdata") {
         setGlobalPtr(tlsBase, memoryPtr);
       }
     }
 
     memoryPtr += seg->size;
   }
 
   // Make space for the memory initialization flag
-  if (WasmSym::initMemoryFlag) {
+  if (config->sharedMemory && hasPassiveInitializedSegments()) {
     memoryPtr = alignTo(memoryPtr, 4);
+    WasmSym::initMemoryFlag = symtab->addSyntheticDataSymbol(
+        "__wasm_init_memory_flag", WASM_SYMBOL_VISIBILITY_HIDDEN);
+    WasmSym::initMemoryFlag->markLive();
     WasmSym::initMemoryFlag->setVirtualAddress(memoryPtr);
     log(formatv("mem: {0,-15} offset={1,-8} size={2,-8} align={3}",
                 "__wasm_init_memory_flag", memoryPtr, 4, 4));
     memoryPtr += 4;
   }
 
   if (WasmSym::dataEnd)
     WasmSym::dataEnd->setVirtualAddress(memoryPtr);

 bool Writer::hasPassiveInitializedSegments() {
   return std::find_if(segments.begin(), segments.end(),
                       [this](const OutputSegment *s) {
                         return this->needsPassiveInitialization(s);
                       }) != segments.end();
 }
 
 void Writer::createSyntheticInitFunctions() {
+  if (config->relocatable)
+    return;
+
+  static WasmSignature nullSignature = {{}, {}};
+
   // Passive segments are used to avoid memory being reinitialized on each
   // thread's instantiation. These passive segments are initialized and
   // dropped in __wasm_init_memory, which is registered as the start function
-
   if (config->sharedMemory && hasPassiveInitializedSegments()) {
-    static WasmSignature nullSignature = {{}, {}};
     WasmSym::initMemory = symtab->addSyntheticFunction(
         "__wasm_init_memory", WASM_SYMBOL_VISIBILITY_HIDDEN,
         make<SyntheticFunction>(nullSignature, "__wasm_init_memory"));
     WasmSym::initMemory->markLive();
-    WasmSym::initMemoryFlag = symtab->addSyntheticDataSymbol(
-        "__wasm_init_memory_flag", WASM_SYMBOL_VISIBILITY_HIDDEN);
-    WasmSym::initMemoryFlag->markLive();
+  }
+
+  if (config->isPic) {
+    // For PIC code we create a synthetic functions that apply relocations.
+    // These get called from __wasm_call_ctors before the user-level
+    // constructors.
+    WasmSym::applyDataRelocs = symtab->addSyntheticFunction(
+        "__wasm_apply_data_relocs", WASM_SYMBOL_VISIBILITY_HIDDEN,
+        make<SyntheticFunction>(nullSignature, "__wasm_apply_data_relocs"));
+    WasmSym::applyDataRelocs->markLive();
+
+    if (out.globalSec->needsRelocations()) {
+      WasmSym::applyGlobalRelocs = symtab->addSyntheticFunction(
+          "__wasm_apply_global_relocs", WASM_SYMBOL_VISIBILITY_HIDDEN,
+          make<SyntheticFunction>(nullSignature, "__wasm_apply_global_relocs"));
+      WasmSym::applyGlobalRelocs->markLive();
+    }
+  }
+
+  if (WasmSym::applyGlobalRelocs && WasmSym::initMemory) {
+    WasmSym::startFunction = symtab->addSyntheticFunction(
+        "__wasm_start", WASM_SYMBOL_VISIBILITY_HIDDEN,
+        make<SyntheticFunction>(nullSignature, "__wasm_start"));
+    WasmSym::startFunction->markLive();
   }
 }
 
 void Writer::createInitMemoryFunction() {
   LLVM_DEBUG(dbgs() << "createInitMemoryFunction\n");
   assert(WasmSym::initMemory);
   assert(WasmSym::initMemoryFlag);
   assert(hasPassiveInitializedSegments());
for (const OutputSegment *s : segments) {
       }
     }
     writeU8(os, WASM_OPCODE_END, "END");
   }
 
   createFunction(WasmSym::initMemory, bodyContent);
 }
 
+void Writer::createStartFunction() {
+  if (WasmSym::startFunction) {
+    std::string bodyContent;
+    {
+      raw_string_ostream os(bodyContent);
+      writeUleb128(os, 0, "num locals");
+      writeU8(os, WASM_OPCODE_CALL, "CALL");
+      writeUleb128(os, WasmSym::initMemory->getFunctionIndex(),
+                   "function index");
+      writeU8(os, WASM_OPCODE_CALL, "CALL");
+      writeUleb128(os, WasmSym::applyGlobalRelocs->getFunctionIndex(),
+                   "function index");
+      writeU8(os, WASM_OPCODE_END, "END");
+    }
+    createFunction(WasmSym::startFunction, bodyContent);
+  } else if (WasmSym::initMemory) {
+    WasmSym::startFunction = WasmSym::initMemory;
+  } else if (WasmSym::applyGlobalRelocs) {
+    WasmSym::startFunction = WasmSym::applyGlobalRelocs;
+  }
+}
+
 // For -shared (PIC) output, we create create a synthetic function which will
 // apply any relocations to the data segments on startup.  This function is
 // called __wasm_apply_relocs and is added at the beginning of __wasm_call_ctors
 // before any of the constructors run.
-void Writer::createApplyRelocationsFunction() {
-  LLVM_DEBUG(dbgs() << "createApplyRelocationsFunction\n");
+void Writer::createApplyDataRelocationsFunction() {
+  LLVM_DEBUG(dbgs() << "createApplyDataRelocationsFunction\n");
   // First write the body's contents to a string.
   std::string bodyContent;
   {
     raw_string_ostream os(bodyContent);
     writeUleb128(os, 0, "num locals");
-
-    // First apply relocations to any internalized GOT entries.  These
-    // are the result of relaxation when building with -Bsymbolic.
-    out.globalSec->generateRelocationCode(os);
-
-    // Next apply any realocation to the data section by reading GOT entry
-    // globals.
     for (const OutputSegment *seg : segments)
       for (const InputSegment *inSeg : seg->inputSegments)
         inSeg->generateRelocationCode(os);
 
     writeU8(os, WASM_OPCODE_END, "END");
   }
 
-  createFunction(WasmSym::applyRelocs, bodyContent);
+  createFunction(WasmSym::applyDataRelocs, bodyContent);
+}
+
+// Similar to createApplyDataRelocationsFunction but generates relocation code
+// fro WebAssembly globals. Because these globals are not shared between threads
+// these relocation need to run on every thread.
+void Writer::createApplyGlobalRelocationsFunction() {
+  // First write the body's contents to a string.
+  std::string bodyContent;
+  {
+    raw_string_ostream os(bodyContent);
+    writeUleb128(os, 0, "num locals");
+    out.globalSec->generateRelocationCode(os);
+    writeU8(os, WASM_OPCODE_END, "END");
+  }
+
+  createFunction(WasmSym::applyGlobalRelocs, bodyContent);
 }
 
 // Create synthetic "__wasm_call_ctors" function based on ctor functions
 // in input object.
 void Writer::createCallCtorsFunction() {
   // If __wasm_call_ctors isn't referenced, there aren't any ctors, and we
   // aren't calling `__wasm_apply_relocs` for Emscripten-style PIC, don't
   // define the `__wasm_call_ctors` function.
-  if (!WasmSym::callCtors->isLive() && initFunctions.empty() && !config->isPic)
+  if (!WasmSym::callCtors->isLive() && !WasmSym::applyDataRelocs &&
+      initFunctions.empty())
     return;
 
   // First write the body's contents to a string.
   std::string bodyContent;
   {
     raw_string_ostream os(bodyContent);
     writeUleb128(os, 0, "num locals");
 
-    if (config->isPic) {
+    if (WasmSym::applyDataRelocs) {
       writeU8(os, WASM_OPCODE_CALL, "CALL");
-      writeUleb128(os, WasmSym::applyRelocs->getFunctionIndex(),
+      writeUleb128(os, WasmSym::applyDataRelocs->getFunctionIndex(),
                    "function index");
     }
 
     // Call constructors
     for (const WasmInitEntry &f : initFunctions) {
       writeU8(os, WASM_OPCODE_CALL, "CALL");
       writeUleb128(os, f.sym->getFunctionIndex(), "function index");
       for (size_t i = 0; i < f.sym->signature->Returns.size(); i++) {
         writeU8(os, WASM_OPCODE_DROP, "DROP");
       }
     }
+
     writeU8(os, WASM_OPCODE_END, "END");
   }
 
   createFunction(WasmSym::callCtors, bodyContent);
 }
 
 // Create a wrapper around a function export which calls the
 // static constructors and destructors.
 void Writer::createCommandExportWrapper(uint32_t functionIndex,
                                         DefinedFunction *f) {
   // First write the body's contents to a string.
   std::string bodyContent;
   {
     raw_string_ostream os(bodyContent);
     writeUleb128(os, 0, "num locals");
 
     // If we have any ctors, or we're calling `__wasm_apply_relocs` for
     // Emscripten-style PIC, call `__wasm_call_ctors` which performs those
     // calls.
-    if (!initFunctions.empty() || config->isPic) {
+    if (WasmSym::callCtors->isLive()) {
       writeU8(os, WASM_OPCODE_CALL, "CALL");
       writeUleb128(os, WasmSym::callCtors->getFunctionIndex(),
                    "function index");
     }
 
     // Call the user's code, leaving any return values on the operand stack.
     for (size_t i = 0; i < f->signature->Params.size(); ++i) {
       writeU8(os, WASM_OPCODE_LOCAL_GET, "local.get");
void Writer::run() {
   log("-- createOutputSegments");
   createOutputSegments();
   log("-- createSyntheticSections");
   createSyntheticSections();
   log("-- populateProducers");
   populateProducers();
   log("-- calculateImports");
   calculateImports();
-  log("-- createSyntheticInitFunctions");
-  createSyntheticInitFunctions();
   log("-- layoutMemory");
   layoutMemory();
 
   if (!config->relocatable) {
     // Create linker synthesized __start_SECNAME/__stop_SECNAME symbols
     // This has to be done after memory layout is performed.
     for (const OutputSegment *seg : segments)
       addStartStopSymbols(seg);
   }
 
   log("-- scanRelocations");
   scanRelocations();
+  log("-- createSyntheticInitFunctions");
+  createSyntheticInitFunctions();
   log("-- assignIndexes");
   assignIndexes();
   log("-- calculateInitFunctions");
   calculateInitFunctions();
 
   if (!config->relocatable) {
-    if (WasmSym::applyRelocs)
-      createApplyRelocationsFunction();
+    // Create linker synthesized functions
+    if (WasmSym::applyDataRelocs)
+      createApplyDataRelocationsFunction();
+    if (WasmSym::applyGlobalRelocs)
+      createApplyGlobalRelocationsFunction();
     if (WasmSym::initMemory)
       createInitMemoryFunction();
+    createStartFunction();
 
-    // Create linker synthesized functions
     createCallCtorsFunction();
 
     // Create export wrappers for commands if needed.
     //
     // If the input contains a call to `__wasm_call_ctors`, either in one of
     // the input objects or an explicit export from the command-line, we
     // assume ctors and dtors are taken care of already.
     if (!config->relocatable && !config->isPic &&