[wasm-ld] Refactor WasmSym from static globals to per-link context (#134970)

anutosh491 · vgvassilev · tstellar · commit 0019b7d0ae0b · 2025-05-10T11:12:53.000-07:00
Towards This change moves WasmSym from a static global struct to an instance owned by Ctx, allowing it to be reset cleanly between linker runs. This enables safe support for multiple invocations of wasm-ld within the same process Changes done - Converted WasmSym from a static struct to a regular struct with instance members. - Added a std::unique_ptr<WasmSym> wasmSym field inside Ctx. - Reset wasmSym in Ctx::reset() to clear state between links. - Replaced all WasmSym:: references with ctx.wasmSym->. - Removed global symbol definitions from Symbols.cpp that are no longer needed. Clearing wasmSym in ctx.reset() ensures a clean slate for each link invocation, preventing symbol leakage across runs—critical when using wasm-ld/lld as a reentrant library where global state can cause subtle, hard-to-debug errors. --------- Co-authored-by: Vassil Vassilev <v.g.vassilev@gmail.com> (cherry picked from commit 9cbbb74)
diff --git a/lld/wasm/Config.h b/lld/wasm/Config.h
@@ -32,6 +32,11 @@ class InputTable;
 class InputGlobal;
 class InputFunction;
 class Symbol;
+class DefinedData;
+class GlobalSymbol;
+class DefinedFunction;
+class UndefinedGlobal;
+class TableSymbol;
 
 // For --unresolved-symbols.
 enum class UnresolvedPolicy { ReportError, Warn, Ignore, ImportDynamic };
@@ -139,6 +144,107 @@ struct Ctx {
   llvm::SmallVector<InputGlobal *, 0> syntheticGlobals;
   llvm::SmallVector<InputTable *, 0> syntheticTables;
 
+  // linker-generated symbols
+  struct WasmSym {
+    // __global_base
+    // Symbol marking the start of the global section.
+    DefinedData *globalBase;
+
+    // __stack_pointer/__stack_low/__stack_high
+    // Global that holds current value of stack pointer and data symbols marking
+    // the start and end of the stack region.  stackPointer is initialized to
+    // stackHigh and grows downwards towards stackLow
+    GlobalSymbol *stackPointer;
+    DefinedData *stackLow;
+    DefinedData *stackHigh;
+
+    // __tls_base
+    // Global that holds the address of the base of the current thread's
+    // TLS block.
+    GlobalSymbol *tlsBase;
+
+    // __tls_size
+    // Symbol whose value is the size of the TLS block.
+    GlobalSymbol *tlsSize;
+
+    // __tls_size
+    // Symbol whose value is the alignment of the TLS block.
+    GlobalSymbol *tlsAlign;
+
+    // __data_end
+    // Symbol marking the end of the data and bss.
+    DefinedData *dataEnd;
+
+    // __heap_base/__heap_end
+    // Symbols marking the beginning and end of the "heap". It starts at the end
+    // of the data, bss and explicit stack, and extends to the end of the linear
+    // memory allocated by wasm-ld. This region of memory is not used by the
+    // linked code, so it may be used as a backing store for `sbrk` or `malloc`
+    // implementations.
+    DefinedData *heapBase;
+    DefinedData *heapEnd;
+
+    // __wasm_init_memory_flag
+    // Symbol whose contents are nonzero iff memory has already been
+    // initialized.
+    DefinedData *initMemoryFlag;
+
+    // __wasm_init_memory
+    // Function that initializes passive data segments during instantiation.
+    DefinedFunction *initMemory;
+
+    // __wasm_call_ctors
+    // Function that directly calls all ctors in priority order.
+    DefinedFunction *callCtors;
+
+    // __wasm_call_dtors
+    // Function that calls the libc/etc. cleanup function.
+    DefinedFunction *callDtors;
+
+    // __wasm_apply_global_relocs
+    // Function that applies relocations to wasm globals post-instantiation.
+    // Unlike __wasm_apply_data_relocs this needs to run on every thread.
+    DefinedFunction *applyGlobalRelocs;
+
+    // __wasm_apply_tls_relocs
+    // Like __wasm_apply_data_relocs but for TLS section.  These must be
+    // delayed until __wasm_init_tls.
+    DefinedFunction *applyTLSRelocs;
+
+    // __wasm_apply_global_tls_relocs
+    // Like applyGlobalRelocs but for globals that hold TLS addresses.  These
+    // must be delayed until __wasm_init_tls.
+    DefinedFunction *applyGlobalTLSRelocs;
+
+    // __wasm_init_tls
+    // Function that allocates thread-local storage and initializes it.
+    DefinedFunction *initTLS;
+
+    // Pointer to the function that is to be used in the start section.
+    // (normally an alias of initMemory, or applyGlobalRelocs).
+    DefinedFunction *startFunction;
+
+    // __dso_handle
+    // Symbol used in calls to __cxa_atexit to determine current DLL
+    DefinedData *dsoHandle;
+
+    // __table_base
+    // Used in PIC code for offset of indirect function table
+    UndefinedGlobal *tableBase;
+    DefinedData *definedTableBase;
+
+    // __memory_base
+    // Used in PIC code for offset of global data
+    UndefinedGlobal *memoryBase;
+    DefinedData *definedMemoryBase;
+
+    // __indirect_function_table
+    // Used as an address space for function pointers, with each function that
+    // is used as a function pointer being allocated a slot.
+    TableSymbol *indirectFunctionTable;
+  };
+  WasmSym sym;
+
   // True if we are creating position-independent code.
   bool isPic = false;
 
diff --git a/lld/wasm/Driver.cpp b/lld/wasm/Driver.cpp
@@ -70,6 +70,7 @@ void Ctx::reset() {
   isPic = false;
   legacyFunctionTable = false;
   emitBssSegments = false;
+  sym = WasmSym{};
 }
 
 namespace {
@@ -941,14 +942,14 @@ static void createSyntheticSymbols() {
                                                             true};
   static llvm::wasm::WasmGlobalType mutableGlobalTypeI64 = {WASM_TYPE_I64,
                                                             true};
-  WasmSym::callCtors = symtab->addSyntheticFunction(
+  ctx.sym.callCtors = symtab->addSyntheticFunction(
       "__wasm_call_ctors", WASM_SYMBOL_VISIBILITY_HIDDEN,
       make<SyntheticFunction>(nullSignature, "__wasm_call_ctors"));
 
   bool is64 = ctx.arg.is64.value_or(false);
 
   if (ctx.isPic) {
-    WasmSym::stackPointer =
+    ctx.sym.stackPointer =
         createUndefinedGlobal("__stack_pointer", ctx.arg.is64.value_or(false)
                                                      ? &mutableGlobalTypeI64
                                                      : &mutableGlobalTypeI32);
@@ -958,45 +959,44 @@ static void createSyntheticSymbols() {
     // See:
     // https://github.com/WebAssembly/tool-conventions/blob/main/DynamicLinking.md
     auto *globalType = is64 ? &globalTypeI64 : &globalTypeI32;
-    WasmSym::memoryBase = createUndefinedGlobal("__memory_base", globalType);
-    WasmSym::tableBase = createUndefinedGlobal("__table_base", globalType);
-    WasmSym::memoryBase->markLive();
-    WasmSym::tableBase->markLive();
+    ctx.sym.memoryBase = createUndefinedGlobal("__memory_base", globalType);
+    ctx.sym.tableBase = createUndefinedGlobal("__table_base", globalType);
+    ctx.sym.memoryBase->markLive();
+    ctx.sym.tableBase->markLive();
   } else {
     // For non-PIC code
-    WasmSym::stackPointer = createGlobalVariable("__stack_pointer", true);
-    WasmSym::stackPointer->markLive();
+    ctx.sym.stackPointer = createGlobalVariable("__stack_pointer", true);
+    ctx.sym.stackPointer->markLive();
   }
 
   if (ctx.arg.sharedMemory) {
-    WasmSym::tlsBase = createGlobalVariable("__tls_base", true);
-    WasmSym::tlsSize = createGlobalVariable("__tls_size", false);
-    WasmSym::tlsAlign = createGlobalVariable("__tls_align", false);
-    WasmSym::initTLS = symtab->addSyntheticFunction(
+    ctx.sym.tlsBase = createGlobalVariable("__tls_base", true);
+    ctx.sym.tlsSize = createGlobalVariable("__tls_size", false);
+    ctx.sym.tlsAlign = createGlobalVariable("__tls_align", false);
+    ctx.sym.initTLS = symtab->addSyntheticFunction(
         "__wasm_init_tls", WASM_SYMBOL_VISIBILITY_HIDDEN,
-        make<SyntheticFunction>(
-            is64 ? i64ArgSignature : i32ArgSignature,
-            "__wasm_init_tls"));
+        make<SyntheticFunction>(is64 ? i64ArgSignature : i32ArgSignature,
+                                "__wasm_init_tls"));
   }
 }
 
 static void createOptionalSymbols() {
   if (ctx.arg.relocatable)
     return;
 
-  WasmSym::dsoHandle = symtab->addOptionalDataSymbol("__dso_handle");
+  ctx.sym.dsoHandle = symtab->addOptionalDataSymbol("__dso_handle");
 
   if (!ctx.arg.shared)
-    WasmSym::dataEnd = symtab->addOptionalDataSymbol("__data_end");
+    ctx.sym.dataEnd = symtab->addOptionalDataSymbol("__data_end");
 
   if (!ctx.isPic) {
-    WasmSym::stackLow = symtab->addOptionalDataSymbol("__stack_low");
-    WasmSym::stackHigh = symtab->addOptionalDataSymbol("__stack_high");
-    WasmSym::globalBase = symtab->addOptionalDataSymbol("__global_base");
-    WasmSym::heapBase = symtab->addOptionalDataSymbol("__heap_base");
-    WasmSym::heapEnd = symtab->addOptionalDataSymbol("__heap_end");
-    WasmSym::definedMemoryBase = symtab->addOptionalDataSymbol("__memory_base");
-    WasmSym::definedTableBase = symtab->addOptionalDataSymbol("__table_base");
+    ctx.sym.stackLow = symtab->addOptionalDataSymbol("__stack_low");
+    ctx.sym.stackHigh = symtab->addOptionalDataSymbol("__stack_high");
+    ctx.sym.globalBase = symtab->addOptionalDataSymbol("__global_base");
+    ctx.sym.heapBase = symtab->addOptionalDataSymbol("__heap_base");
+    ctx.sym.heapEnd = symtab->addOptionalDataSymbol("__heap_end");
+    ctx.sym.definedMemoryBase = symtab->addOptionalDataSymbol("__memory_base");
+    ctx.sym.definedTableBase = symtab->addOptionalDataSymbol("__table_base");
   }
 
   // For non-shared memory programs we still need to define __tls_base since we
@@ -1009,7 +1009,7 @@ static void createOptionalSymbols() {
   // __tls_size and __tls_align are not needed in this case since they are only
   // needed for __wasm_init_tls (which we do not create in this case).
   if (!ctx.arg.sharedMemory)
-    WasmSym::tlsBase = createOptionalGlobal("__tls_base", false);
+    ctx.sym.tlsBase = createOptionalGlobal("__tls_base", false);
 }
 
 static void processStubLibrariesPreLTO() {
@@ -1384,9 +1384,9 @@ void LinkerDriver::linkerMain(ArrayRef<const char *> argsArr) {
   // by libc/etc., because destructors are registered dynamically with
   // `__cxa_atexit` and friends.
   if (!ctx.arg.relocatable && !ctx.arg.shared &&
-      !WasmSym::callCtors->isUsedInRegularObj &&
-      WasmSym::callCtors->getName() != ctx.arg.entry &&
-      !ctx.arg.exportedSymbols.count(WasmSym::callCtors->getName())) {
+      !ctx.sym.callCtors->isUsedInRegularObj &&
+      ctx.sym.callCtors->getName() != ctx.arg.entry &&
+      !ctx.arg.exportedSymbols.count(ctx.sym.callCtors->getName())) {
     if (Symbol *callDtors =
             handleUndefined("__wasm_call_dtors", "<internal>")) {
       if (auto *callDtorsFunc = dyn_cast<DefinedFunction>(callDtors)) {
@@ -1395,7 +1395,7 @@ void LinkerDriver::linkerMain(ArrayRef<const char *> argsArr) {
              !callDtorsFunc->signature->Returns.empty())) {
           error("__wasm_call_dtors must have no argument or return values");
         }
-        WasmSym::callDtors = callDtorsFunc;
+        ctx.sym.callDtors = callDtorsFunc;
       } else {
         error("__wasm_call_dtors must be a function");
       }
@@ -1488,7 +1488,7 @@ void LinkerDriver::linkerMain(ArrayRef<const char *> argsArr) {
   markLive();
 
   // Provide the indirect function table if needed.
-  WasmSym::indirectFunctionTable =
+  ctx.sym.indirectFunctionTable =
       symtab->resolveIndirectFunctionTable(/*required =*/false);
 
   if (errorCount())
diff --git a/lld/wasm/InputChunks.cpp b/lld/wasm/InputChunks.cpp
@@ -397,9 +397,9 @@ bool InputChunk::generateRelocationCode(raw_ostream &os) const {
     if (ctx.isPic) {
       writeU8(os, WASM_OPCODE_GLOBAL_GET, "GLOBAL_GET");
       if (isTLS())
-        writeUleb128(os, WasmSym::tlsBase->getGlobalIndex(), "tls_base");
+        writeUleb128(os, ctx.sym.tlsBase->getGlobalIndex(), "tls_base");
       else
-        writeUleb128(os, WasmSym::memoryBase->getGlobalIndex(), "memory_base");
+        writeUleb128(os, ctx.sym.memoryBase->getGlobalIndex(), "memory_base");
       writeU8(os, opcode_ptr_add, "ADD");
     }
 
@@ -422,12 +422,12 @@ bool InputChunk::generateRelocationCode(raw_ostream &os) const {
       }
     } else {
       assert(ctx.isPic);
-      const GlobalSymbol* baseSymbol = WasmSym::memoryBase;
+      const GlobalSymbol *baseSymbol = ctx.sym.memoryBase;
       if (rel.Type == R_WASM_TABLE_INDEX_I32 ||
           rel.Type == R_WASM_TABLE_INDEX_I64)
-        baseSymbol = WasmSym::tableBase;
+        baseSymbol = ctx.sym.tableBase;
       else if (sym->isTLS())
-        baseSymbol = WasmSym::tlsBase;
+        baseSymbol = ctx.sym.tlsBase;
       writeU8(os, WASM_OPCODE_GLOBAL_GET, "GLOBAL_GET");
       writeUleb128(os, baseSymbol->getGlobalIndex(), "base");
       writeU8(os, opcode_reloc_const, "CONST");
diff --git a/lld/wasm/MarkLive.cpp b/lld/wasm/MarkLive.cpp
@@ -114,8 +114,8 @@ void MarkLive::run() {
     if (sym->isNoStrip() || sym->isExported())
       enqueue(sym);
 
-  if (WasmSym::callDtors)
-    enqueue(WasmSym::callDtors);
+  if (ctx.sym.callDtors)
+    enqueue(ctx.sym.callDtors);
 
   for (const ObjFile *obj : ctx.objectFiles)
     if (obj->isLive()) {
@@ -131,7 +131,7 @@ void MarkLive::run() {
   // If we have any non-discarded init functions, mark `__wasm_call_ctors` as
   // live so that we assign it an index and call it.
   if (isCallCtorsLive())
-    WasmSym::callCtors->markLive();
+    ctx.sym.callCtors->markLive();
 }
 
 void MarkLive::mark() {
diff --git a/lld/wasm/OutputSections.cpp b/lld/wasm/OutputSections.cpp
@@ -123,7 +123,7 @@ void DataSection::finalizeContents() {
     if ((segment->initFlags & WASM_DATA_SEGMENT_IS_PASSIVE) == 0) {
       if (ctx.isPic && ctx.arg.extendedConst) {
         writeU8(os, WASM_OPCODE_GLOBAL_GET, "global get");
-        writeUleb128(os, WasmSym::memoryBase->getGlobalIndex(),
+        writeUleb128(os, ctx.sym.memoryBase->getGlobalIndex(),
                      "literal (global index)");
         if (segment->startVA) {
           writePtrConst(os, segment->startVA, is64, "offset");
@@ -136,7 +136,7 @@ void DataSection::finalizeContents() {
         if (ctx.isPic) {
           assert(segment->startVA == 0);
           initExpr.Inst.Opcode = WASM_OPCODE_GLOBAL_GET;
-          initExpr.Inst.Value.Global = WasmSym::memoryBase->getGlobalIndex();
+          initExpr.Inst.Value.Global = ctx.sym.memoryBase->getGlobalIndex();
         } else {
           initExpr = intConst(segment->startVA, is64);
         }
diff --git a/lld/wasm/Symbols.cpp b/lld/wasm/Symbols.cpp
@@ -77,31 +77,6 @@ std::string toString(wasm::Symbol::Kind kind) {
 }
 
 namespace wasm {
-DefinedFunction *WasmSym::callCtors;
-DefinedFunction *WasmSym::callDtors;
-DefinedFunction *WasmSym::initMemory;
-DefinedFunction *WasmSym::applyGlobalRelocs;
-DefinedFunction *WasmSym::applyTLSRelocs;
-DefinedFunction *WasmSym::applyGlobalTLSRelocs;
-DefinedFunction *WasmSym::initTLS;
-DefinedFunction *WasmSym::startFunction;
-DefinedData *WasmSym::dsoHandle;
-DefinedData *WasmSym::dataEnd;
-DefinedData *WasmSym::globalBase;
-DefinedData *WasmSym::heapBase;
-DefinedData *WasmSym::heapEnd;
-DefinedData *WasmSym::initMemoryFlag;
-GlobalSymbol *WasmSym::stackPointer;
-DefinedData *WasmSym::stackLow;
-DefinedData *WasmSym::stackHigh;
-GlobalSymbol *WasmSym::tlsBase;
-GlobalSymbol *WasmSym::tlsSize;
-GlobalSymbol *WasmSym::tlsAlign;
-UndefinedGlobal *WasmSym::tableBase;
-DefinedData *WasmSym::definedTableBase;
-UndefinedGlobal *WasmSym::memoryBase;
-DefinedData *WasmSym::definedMemoryBase;
-TableSymbol *WasmSym::indirectFunctionTable;
 
 WasmSymbolType Symbol::getWasmType() const {
   if (isa<FunctionSymbol>(this))
diff --git a/lld/wasm/Symbols.h b/lld/wasm/Symbols.h
diff --git a/lld/wasm/SyntheticSections.cpp b/lld/wasm/SyntheticSections.cpp
diff --git a/lld/wasm/Writer.cpp b/lld/wasm/Writer.cpp

-Original file line number
+Diff line change
   // Some inputs require that the indirect function table be assigned to table
   // number 0.
   if (ctx.legacyFunctionTable &&
 -      isa<DefinedTable>(WasmSym::indirectFunctionTable) &&
 -      cast<DefinedTable>(WasmSym::indirectFunctionTable)->table == table) {
 +      isa<DefinedTable>(ctx.sym.indirectFunctionTable) &&
 +      cast<DefinedTable>(ctx.sym.indirectFunctionTable)->table == table) {
     if (out.importSec->getNumImportedTables()) {
       // Alack!  Some other input imported a table, meaning that we are unable
       // to assign table number 0 to the indirect function table.
+}
 static void ensureIndirectFunctionTable() {
 -  if (!WasmSym::indirectFunctionTable)
 -    WasmSym::indirectFunctionTable =
 +  if (!ctx.sym.indirectFunctionTable)
 +    ctx.sym.indirectFunctionTable =
         symtab->resolveIndirectFunctionTable(/*required =*/true);
+}
       // Get __memory_base
       writeU8(os, WASM_OPCODE_GLOBAL_GET, "GLOBAL_GET");
       if (sym->isTLS())
 -        writeUleb128(os, WasmSym::tlsBase->getGlobalIndex(), "__tls_base");
 +        writeUleb128(os, ctx.sym.tlsBase->getGlobalIndex(), "__tls_base");
       else
 -        writeUleb128(os, WasmSym::memoryBase->getGlobalIndex(),
 -                     "__memory_base");
 +        writeUleb128(os, ctx.sym.memoryBase->getGlobalIndex(), "__memory_base");
       // Add the virtual address of the data symbol
       writeU8(os, opcode_ptr_const, "CONST");
         continue;
       // Get __table_base
       writeU8(os, WASM_OPCODE_GLOBAL_GET, "GLOBAL_GET");
 -      writeUleb128(os, WasmSym::tableBase->getGlobalIndex(), "__table_base");
 +      writeUleb128(os, ctx.sym.tableBase->getGlobalIndex(), "__table_base");
       // Add the table index to __table_base
       writeU8(os, opcode_ptr_const, "CONST");
     if (ctx.arg.extendedConst && ctx.isPic) {
       if (auto *d = dyn_cast<DefinedData>(sym)) {
         if (!sym->isTLS()) {
 -          globalIdx = WasmSym::memoryBase->getGlobalIndex();
 +          globalIdx = ctx.sym.memoryBase->getGlobalIndex();
           offset = d->getVA();
           useExtendedConst = true;
+        }
       } else if (auto *f = dyn_cast<FunctionSymbol>(sym)) {
         if (!sym->isStub) {
 -          globalIdx = WasmSym::tableBase->getGlobalIndex();
 +          globalIdx = ctx.sym.tableBase->getGlobalIndex();
           offset = f->getTableIndex();
           useExtendedConst = true;
+        }
     writeExport(os, export_);
+}
 -bool StartSection::isNeeded() const {
 -  return WasmSym::startFunction != nullptr;
 -}
 +bool StartSection::isNeeded() const { return ctx.sym.startFunction != nullptr; }
 void StartSection::writeBody() {
   raw_ostream &os = bodyOutputStream;
 -  writeUleb128(os, WasmSym::startFunction->getFunctionIndex(),
 -               "function index");
 +  writeUleb128(os, ctx.sym.startFunction->getFunctionIndex(), "function index");
+}
 void ElemSection::addEntry(FunctionSymbol *sym) {
 void ElemSection::writeBody() {
   raw_ostream &os = bodyOutputStream;
 -  assert(WasmSym::indirectFunctionTable);
 +  assert(ctx.sym.indirectFunctionTable);
   writeUleb128(os, 1, "segment count");
 -  uint32_t tableNumber = WasmSym::indirectFunctionTable->getTableNumber();
 +  uint32_t tableNumber = ctx.sym.indirectFunctionTable->getTableNumber();
   uint32_t flags = 0;
   if (tableNumber)
     flags |= WASM_ELEM_SEGMENT_HAS_TABLE_NUMBER;
   initExpr.Extended = false;
   if (ctx.isPic) {
     initExpr.Inst.Opcode = WASM_OPCODE_GLOBAL_GET;
 -    initExpr.Inst.Value.Global = WasmSym::tableBase->getGlobalIndex();
 +    initExpr.Inst.Value.Global = ctx.sym.tableBase->getGlobalIndex();
   } else {
     bool is64 = ctx.arg.is64.value_or(false);
     initExpr = intConst(ctx.arg.tableBase, is64);