king
/
v811_spc009
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '8f4c154c05'
${ noResults }
v811_spc009/external/llvm-project/lld/wasm/Writer.cpp

1358 lines
46 KiB
Raw Blame History

//===- Writer.cpp ---------------------------------------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#include "Writer.h"
#include "Config.h"
#include "InputChunks.h"
#include "InputEvent.h"
#include "InputGlobal.h"
#include "MapFile.h"
#include "OutputSections.h"
#include "OutputSegment.h"
#include "Relocations.h"
#include "SymbolTable.h"
#include "SyntheticSections.h"
#include "WriterUtils.h"
#include "lld/Common/ErrorHandler.h"
#include "lld/Common/Memory.h"
#include "lld/Common/Strings.h"
#include "llvm/ADT/DenseSet.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringMap.h"
#include "llvm/BinaryFormat/Wasm.h"
#include "llvm/BinaryFormat/WasmTraits.h"
#include "llvm/Support/FileOutputBuffer.h"
#include "llvm/Support/Format.h"
#include "llvm/Support/FormatVariadic.h"
#include "llvm/Support/LEB128.h"
#include "llvm/Support/Parallel.h"
#include <cstdarg>
#include <map>
#define DEBUG_TYPE "lld"
using namespace llvm;
using namespace llvm::wasm;
namespace lld {
namespace wasm {
static constexpr int stackAlignment = 16;
namespace {
// The writer writes a SymbolTable result to a file.
class Writer {
public:
void run();
private:
void openFile();
bool needsPassiveInitialization(const OutputSegment *segment);
bool hasPassiveInitializedSegments();
void createInitMemoryFunction();
void createApplyRelocationsFunction();
void createCallCtorsFunction();
void createInitTLSFunction();
void createCommandExportWrappers();
void createCommandExportWrapper(uint32_t functionIndex, DefinedFunction *f);
void assignIndexes();
void populateSymtab();
void populateProducers();
void populateTargetFeatures();
void calculateInitFunctions();
void calculateImports();
void calculateExports();
void calculateCustomSections();
void calculateTypes();
void createOutputSegments();
void layoutMemory();
void createHeader();
void addSection(OutputSection *sec);
void addSections();
void createCustomSections();
void createSyntheticSections();
void finalizeSections();
// Custom sections
void createRelocSections();
void writeHeader();
void writeSections();
uint64_t fileSize = 0;
std::vector<WasmInitEntry> initFunctions;
llvm::StringMap<std::vector<InputSection *>> customSectionMapping;
// Stable storage for command export wrapper function name strings.
std::list<std::string> commandExportWrapperNames;
// Elements that are used to construct the final output
std::string header;
std::vector<OutputSection *> outputSections;
std::unique_ptr<FileOutputBuffer> buffer;
std::vector<OutputSegment *> segments;
llvm::SmallDenseMap<StringRef, OutputSegment *> segmentMap;
};
} // anonymous namespace
void Writer::calculateCustomSections() {
log("calculateCustomSections");
bool stripDebug = config->stripDebug || config->stripAll;
for (ObjFile *file : symtab->objectFiles) {
for (InputSection *section : file->customSections) {
StringRef name = section->getName();
// These custom sections are known the linker and synthesized rather than
// blindly copied.
if (name == "linking" || name == "name" || name == "producers" ||
name == "target_features" || name.startswith("reloc."))
continue;
// These custom sections are generated by `clang -fembed-bitcode`.
// These are used by the rust toolchain to ship LTO data along with
// compiled object code, but they don't want this included in the linker
// output.
if (name == ".llvmbc" || name == ".llvmcmd")
continue;
// Strip debug section in that option was specified.
if (stripDebug && name.startswith(".debug_"))
continue;
// Otherwise include custom sections by default and concatenate their
// contents.
customSectionMapping[name].push_back(section);
}
}
}
void Writer::createCustomSections() {
log("createCustomSections");
for (auto &pair : customSectionMapping) {
StringRef name = pair.first();
LLVM_DEBUG(dbgs() << "createCustomSection: " << name << "\n");
OutputSection *sec = make<CustomSection>(std::string(name), pair.second);
if (config->relocatable || config->emitRelocs) {
auto *sym = make<OutputSectionSymbol>(sec);
out.linkingSec->addToSymtab(sym);
sec->sectionSym = sym;
}
addSection(sec);
}
}
// Create relocations sections in the final output.
// These are only created when relocatable output is requested.
void Writer::createRelocSections() {
log("createRelocSections");
// Don't use iterator here since we are adding to OutputSection
size_t origSize = outputSections.size();
for (size_t i = 0; i < origSize; i++) {
LLVM_DEBUG(dbgs() << "check section " << i << "\n");
OutputSection *sec = outputSections[i];
// Count the number of needed sections.
uint32_t count = sec->getNumRelocations();
if (!count)
continue;
StringRef name;
if (sec->type == WASM_SEC_DATA)
name = "reloc.DATA";
else if (sec->type == WASM_SEC_CODE)
name = "reloc.CODE";
else if (sec->type == WASM_SEC_CUSTOM)
name = saver.save("reloc." + sec->name);
else
llvm_unreachable(
"relocations only supported for code, data, or custom sections");
addSection(make<RelocSection>(name, sec));
}
}
void Writer::populateProducers() {
for (ObjFile *file : symtab->objectFiles) {
const WasmProducerInfo &info = file->getWasmObj()->getProducerInfo();
out.producersSec->addInfo(info);
}
}
void Writer::writeHeader() {
memcpy(buffer->getBufferStart(), header.data(), header.size());
}
void Writer::writeSections() {
uint8_t *buf = buffer->getBufferStart();
parallelForEach(outputSections, [buf](OutputSection *s) {
assert(s->isNeeded());
s->writeTo(buf);
});
}
static void setGlobalPtr(DefinedGlobal *g, uint64_t memoryPtr) {
if (config->is64.getValueOr(false)) {
assert(g->global->global.InitExpr.Opcode == WASM_OPCODE_I64_CONST);
g->global->global.InitExpr.Value.Int64 = memoryPtr;
} else {
assert(g->global->global.InitExpr.Opcode == WASM_OPCODE_I32_CONST);
g->global->global.InitExpr.Value.Int32 = memoryPtr;
}
}
// Fix the memory layout of the output binary. This assigns memory offsets
// to each of the input data sections as well as the explicit stack region.
// The default memory layout is as follows, from low to high.
//
// - initialized data (starting at Config->globalBase)
// - BSS data (not currently implemented in llvm)
// - explicit stack (Config->ZStackSize)
// - heap start / unallocated
//
// The --stack-first option means that stack is placed before any static data.
// This can be useful since it means that stack overflow traps immediately
// rather than overwriting global data, but also increases code size since all
// static data loads and stores requires larger offsets.
void Writer::layoutMemory() {
uint64_t memoryPtr = 0;
auto placeStack = [&]() {
if (config->relocatable || config->isPic)
return;
memoryPtr = alignTo(memoryPtr, stackAlignment);
if (config->zStackSize != alignTo(config->zStackSize, stackAlignment))
error("stack size must be " + Twine(stackAlignment) + "-byte aligned");
log("mem: stack size = " + Twine(config->zStackSize));
log("mem: stack base = " + Twine(memoryPtr));
memoryPtr += config->zStackSize;
auto *sp = cast<DefinedGlobal>(WasmSym::stackPointer);
switch (sp->global->global.InitExpr.Opcode) {
case WASM_OPCODE_I32_CONST:
sp->global->global.InitExpr.Value.Int32 = memoryPtr;
break;
case WASM_OPCODE_I64_CONST:
sp->global->global.InitExpr.Value.Int64 = memoryPtr;
break;
default:
llvm_unreachable("init expr must be i32/i64.const");
}
log("mem: stack top = " + Twine(memoryPtr));
};
if (config->stackFirst) {
placeStack();
} else {
memoryPtr = config->globalBase;
log("mem: global base = " + Twine(config->globalBase));
}
if (WasmSym::globalBase)
WasmSym::globalBase->setVirtualAddress(memoryPtr);
uint64_t dataStart = memoryPtr;
// Arbitrarily set __dso_handle handle to point to the start of the data
// segments.
if (WasmSym::dsoHandle)
WasmSym::dsoHandle->setVirtualAddress(dataStart);
out.dylinkSec->memAlign = 0;
for (OutputSegment *seg : segments) {
out.dylinkSec->memAlign = std::max(out.dylinkSec->memAlign, seg->alignment);
memoryPtr = alignTo(memoryPtr, 1ULL << seg->alignment);
seg->startVA = memoryPtr;
log(formatv("mem: {0,-15} offset={1,-8} size={2,-8} align={3}", seg->name,
memoryPtr, seg->size, seg->alignment));
if (seg->name == ".tdata") {
if (config->sharedMemory) {
auto *tlsSize = cast<DefinedGlobal>(WasmSym::tlsSize);
setGlobalPtr(tlsSize, seg->size);
auto *tlsAlign = cast<DefinedGlobal>(WasmSym::tlsAlign);
setGlobalPtr(tlsAlign, int64_t{1} << seg->alignment);
} else {
auto *tlsBase = cast<DefinedGlobal>(WasmSym::tlsBase);
setGlobalPtr(tlsBase, memoryPtr);
}
}
memoryPtr += seg->size;
}
// Make space for the memory initialization flag
if (WasmSym::initMemoryFlag) {
memoryPtr = alignTo(memoryPtr, 4);
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);
uint64_t staticDataSize = memoryPtr - dataStart;
log("mem: static data = " + Twine(staticDataSize));
if (config->isPic)
out.dylinkSec->memSize = staticDataSize;
if (!config->stackFirst)
placeStack();
if (WasmSym::heapBase) {
// Set `__heap_base` to directly follow the end of the stack or global data.
// The fact that this comes last means that a malloc/brk implementation
// can grow the heap at runtime.
log("mem: heap base = " + Twine(memoryPtr));
WasmSym::heapBase->setVirtualAddress(memoryPtr);
}
uint64_t maxMemorySetting = 1ULL
<< (config->is64.getValueOr(false) ? 48 : 32);
if (config->initialMemory != 0) {
if (config->initialMemory != alignTo(config->initialMemory, WasmPageSize))
error("initial memory must be " + Twine(WasmPageSize) + "-byte aligned");
if (memoryPtr > config->initialMemory)
error("initial memory too small, " + Twine(memoryPtr) + " bytes needed");
if (config->initialMemory > maxMemorySetting)
error("initial memory too large, cannot be greater than " +
Twine(maxMemorySetting));
memoryPtr = config->initialMemory;
}
out.memorySec->numMemoryPages =
alignTo(memoryPtr, WasmPageSize) / WasmPageSize;
log("mem: total pages = " + Twine(out.memorySec->numMemoryPages));
if (config->maxMemory != 0) {
if (config->maxMemory != alignTo(config->maxMemory, WasmPageSize))
error("maximum memory must be " + Twine(WasmPageSize) + "-byte aligned");
if (memoryPtr > config->maxMemory)
error("maximum memory too small, " + Twine(memoryPtr) + " bytes needed");
if (config->maxMemory > maxMemorySetting)
error("maximum memory too large, cannot be greater than " +
Twine(maxMemorySetting));
}
// Check max if explicitly supplied or required by shared memory
if (config->maxMemory != 0 || config->sharedMemory) {
uint64_t max = config->maxMemory;
if (max == 0) {
// If no maxMemory config was supplied but we are building with
// shared memory, we need to pick a sensible upper limit.
if (config->isPic)
max = maxMemorySetting;
else
max = alignTo(memoryPtr, WasmPageSize);
}
out.memorySec->maxMemoryPages = max / WasmPageSize;
log("mem: max pages = " + Twine(out.memorySec->maxMemoryPages));
}
}
void Writer::addSection(OutputSection *sec) {
if (!sec->isNeeded())
return;
log("addSection: " + toString(*sec));
sec->sectionIndex = outputSections.size();
outputSections.push_back(sec);
}
// If a section name is valid as a C identifier (which is rare because of
// the leading '.'), linkers are expected to define __start_<secname> and
// __stop_<secname> symbols. They are at beginning and end of the section,
// respectively. This is not requested by the ELF standard, but GNU ld and
// gold provide the feature, and used by many programs.
static void addStartStopSymbols(const OutputSegment *seg) {
StringRef name = seg->name;
if (!isValidCIdentifier(name))
return;
LLVM_DEBUG(dbgs() << "addStartStopSymbols: " << name << "\n");
uint64_t start = seg->startVA;
uint64_t stop = start + seg->size;
symtab->addOptionalDataSymbol(saver.save("__start_" + name), start);
symtab->addOptionalDataSymbol(saver.save("__stop_" + name), stop);
}
void Writer::addSections() {
addSection(out.dylinkSec);
addSection(out.typeSec);
addSection(out.importSec);
addSection(out.functionSec);
addSection(out.tableSec);
addSection(out.memorySec);
addSection(out.eventSec);
addSection(out.globalSec);
addSection(out.exportSec);
addSection(out.startSec);
addSection(out.elemSec);
addSection(out.dataCountSec);
addSection(make<CodeSection>(out.functionSec->inputFunctions));
addSection(make<DataSection>(segments));
createCustomSections();
addSection(out.linkingSec);
if (config->emitRelocs || config->relocatable) {
createRelocSections();
}
addSection(out.nameSec);
addSection(out.producersSec);
addSection(out.targetFeaturesSec);
}
void Writer::finalizeSections() {
for (OutputSection *s : outputSections) {
s->setOffset(fileSize);
s->finalizeContents();
fileSize += s->getSize();
}
}
void Writer::populateTargetFeatures() {
StringMap<std::string> used;
StringMap<std::string> required;
StringMap<std::string> disallowed;
SmallSet<std::string, 8> &allowed = out.targetFeaturesSec->features;
bool tlsUsed = false;
// Only infer used features if user did not specify features
bool inferFeatures = !config->features.hasValue();
if (!inferFeatures) {
auto &explicitFeatures = config->features.getValue();
allowed.insert(explicitFeatures.begin(), explicitFeatures.end());
if (!config->checkFeatures)
return;
}
// Find the sets of used, required, and disallowed features
for (ObjFile *file : symtab->objectFiles) {
StringRef fileName(file->getName());
for (auto &feature : file->getWasmObj()->getTargetFeatures()) {
switch (feature.Prefix) {
case WASM_FEATURE_PREFIX_USED:
used.insert({feature.Name, std::string(fileName)});
break;
case WASM_FEATURE_PREFIX_REQUIRED:
used.insert({feature.Name, std::string(fileName)});
required.insert({feature.Name, std::string(fileName)});
break;
case WASM_FEATURE_PREFIX_DISALLOWED:
disallowed.insert({feature.Name, std::string(fileName)});
break;
default:
error("Unrecognized feature policy prefix " +
std::to_string(feature.Prefix));
}
}
// Find TLS data segments
auto isTLS = [](InputSegment *segment) {
StringRef name = segment->getName();
return segment->live &&
(name.startswith(".tdata") || name.startswith(".tbss"));
};
tlsUsed = tlsUsed ||
std::any_of(file->segments.begin(), file->segments.end(), isTLS);
}
if (inferFeatures)
for (const auto &key : used.keys())
allowed.insert(std::string(key));
if (!config->checkFeatures)
return;
if (!config->relocatable && allowed.count("mutable-globals") == 0) {
for (const Symbol *sym : out.importSec->importedSymbols) {
if (auto *global = dyn_cast<GlobalSymbol>(sym)) {
if (global->getGlobalType()->Mutable) {
error(Twine("mutable global imported but 'mutable-globals' feature "
"not present in inputs: `") +
toString(*sym) + "`. Use --no-check-features to suppress.");
}
}
}
for (const Symbol *sym : out.exportSec->exportedSymbols) {
if (isa<GlobalSymbol>(sym)) {
error(Twine("mutable global exported but 'mutable-globals' feature "
"not present in inputs: `") +
toString(*sym) + "`. Use --no-check-features to suppress.");
}
}
}
if (config->sharedMemory) {
if (disallowed.count("shared-mem"))
error("--shared-memory is disallowed by " + disallowed["shared-mem"] +
" because it was not compiled with 'atomics' or 'bulk-memory' "
"features.");
for (auto feature : {"atomics", "bulk-memory"})
if (!allowed.count(feature))
error(StringRef("'") + feature +
"' feature must be used in order to use shared memory");
}
if (tlsUsed) {
for (auto feature : {"atomics", "bulk-memory"})
if (!allowed.count(feature))
error(StringRef("'") + feature +
"' feature must be used in order to use thread-local storage");
}
// Validate that used features are allowed in output
if (!inferFeatures) {
for (auto &feature : used.keys()) {
if (!allowed.count(std::string(feature)))
error(Twine("Target feature '") + feature + "' used by " +
used[feature] + " is not allowed.");
}
}
// Validate the required and disallowed constraints for each file
for (ObjFile *file : symtab->objectFiles) {
StringRef fileName(file->getName());
SmallSet<std::string, 8> objectFeatures;
for (auto &feature : file->getWasmObj()->getTargetFeatures()) {
if (feature.Prefix == WASM_FEATURE_PREFIX_DISALLOWED)
continue;
objectFeatures.insert(feature.Name);
if (disallowed.count(feature.Name))
error(Twine("Target feature '") + feature.Name + "' used in " +
fileName + " is disallowed by " + disallowed[feature.Name] +
". Use --no-check-features to suppress.");
}
for (auto &feature : required.keys()) {
if (!objectFeatures.count(std::string(feature)))
error(Twine("Missing target feature '") + feature + "' in " + fileName +
", required by " + required[feature] +
". Use --no-check-features to suppress.");
}
}
}
static bool shouldImport(Symbol *sym) {
// We don't generate imports for data symbols. They however can be imported
// as GOT entries.
if (isa<DataSymbol>(sym))
return false;
if (config->relocatable ||
config->unresolvedSymbols == UnresolvedPolicy::ImportFuncs)
return true;
if (config->allowUndefinedSymbols.count(sym->getName()) != 0)
return true;
if (auto *g = dyn_cast<UndefinedGlobal>(sym))
return g->importName.hasValue();
if (auto *f = dyn_cast<UndefinedFunction>(sym))
return f->importName.hasValue();
return false;
}
void Writer::calculateImports() {
for (Symbol *sym : symtab->getSymbols()) {
if (!sym->isUndefined())
continue;
if (sym->isWeak() && !config->relocatable)
continue;
if (!sym->isLive())
continue;
if (!sym->isUsedInRegularObj)
continue;
if (shouldImport(sym)) {
LLVM_DEBUG(dbgs() << "import: " << sym->getName() << "\n");
out.importSec->addImport(sym);
}
}
}
void Writer::calculateExports() {
if (config->relocatable)
return;
if (!config->relocatable && !config->importMemory)
out.exportSec->exports.push_back(
WasmExport{"memory", WASM_EXTERNAL_MEMORY, 0});
if (!config->relocatable && config->exportTable)
out.exportSec->exports.push_back(
WasmExport{functionTableName, WASM_EXTERNAL_TABLE, 0});
unsigned globalIndex =
out.importSec->getNumImportedGlobals() + out.globalSec->numGlobals();
for (Symbol *sym : symtab->getSymbols()) {
if (!sym->isExported())
continue;
if (!sym->isLive())
continue;
StringRef name = sym->getName();
WasmExport export_;
if (auto *f = dyn_cast<DefinedFunction>(sym)) {
if (Optional<StringRef> exportName = f->function->getExportName()) {
name = *exportName;
}
export_ = {name, WASM_EXTERNAL_FUNCTION, f->getFunctionIndex()};
} else if (auto *g = dyn_cast<DefinedGlobal>(sym)) {
if (g->getGlobalType()->Mutable && !g->getFile() && !g->forceExport) {
// Avoid exporting mutable globals are linker synthesized (e.g.
// __stack_pointer or __tls_base) unless they are explicitly exported
// from the command line.
// Without this check `--export-all` would cause any program using the
// stack pointer to export a mutable global even if none of the input
// files were built with the `mutable-globals` feature.
continue;
}
export_ = {name, WASM_EXTERNAL_GLOBAL, g->getGlobalIndex()};
} else if (auto *e = dyn_cast<DefinedEvent>(sym)) {
export_ = {name, WASM_EXTERNAL_EVENT, e->getEventIndex()};
} else {
auto *d = cast<DefinedData>(sym);
out.globalSec->dataAddressGlobals.push_back(d);
export_ = {name, WASM_EXTERNAL_GLOBAL, globalIndex++};
}
LLVM_DEBUG(dbgs() << "Export: " << name << "\n");
out.exportSec->exports.push_back(export_);
out.exportSec->exportedSymbols.push_back(sym);
}
}
void Writer::populateSymtab() {
if (!config->relocatable && !config->emitRelocs)
return;
for (Symbol *sym : symtab->getSymbols())
if (sym->isUsedInRegularObj && sym->isLive())
out.linkingSec->addToSymtab(sym);
for (ObjFile *file : symtab->objectFiles) {
LLVM_DEBUG(dbgs() << "Local symtab entries: " << file->getName() << "\n");
for (Symbol *sym : file->getSymbols())
if (sym->isLocal() && !isa<SectionSymbol>(sym) && sym->isLive())
out.linkingSec->addToSymtab(sym);
}
}
void Writer::calculateTypes() {
// The output type section is the union of the following sets:
// 1. Any signature used in the TYPE relocation
// 2. The signatures of all imported functions
// 3. The signatures of all defined functions
// 4. The signatures of all imported events
// 5. The signatures of all defined events
for (ObjFile *file : symtab->objectFiles) {
ArrayRef<WasmSignature> types = file->getWasmObj()->types();
for (uint32_t i = 0; i < types.size(); i++)
if (file->typeIsUsed[i])
file->typeMap[i] = out.typeSec->registerType(types[i]);
}
for (const Symbol *sym : out.importSec->importedSymbols) {
if (auto *f = dyn_cast<FunctionSymbol>(sym))
out.typeSec->registerType(*f->signature);
else if (auto *e = dyn_cast<EventSymbol>(sym))
out.typeSec->registerType(*e->signature);
}
for (const InputFunction *f : out.functionSec->inputFunctions)
out.typeSec->registerType(f->signature);
for (const InputEvent *e : out.eventSec->inputEvents)
out.typeSec->registerType(e->signature);
}
// In a command-style link, create a wrapper for each exported symbol
// which calls the constructors and destructors.
void Writer::createCommandExportWrappers() {
// This logic doesn't currently support Emscripten-style PIC mode.
assert(!config->isPic);
// If there are no ctors and there's no libc `__wasm_call_dtors` to
// call, don't wrap the exports.
if (initFunctions.empty() && WasmSym::callDtors == NULL)
return;
std::vector<DefinedFunction *> toWrap;
for (Symbol *sym : symtab->getSymbols())
if (sym->isExported())
if (auto *f = dyn_cast<DefinedFunction>(sym))
toWrap.push_back(f);
for (auto *f : toWrap) {
auto funcNameStr = (f->getName() + ".command_export").str();
commandExportWrapperNames.push_back(funcNameStr);
const std::string &funcName = commandExportWrapperNames.back();
auto func = make<SyntheticFunction>(*f->getSignature(), funcName);
if (f->function->getExportName().hasValue())
func->setExportName(f->function->getExportName()->str());
else
func->setExportName(f->getName().str());
DefinedFunction *def =
symtab->addSyntheticFunction(funcName, f->flags, func);
def->markLive();
def->flags |= WASM_SYMBOL_EXPORTED;
def->flags &= ~WASM_SYMBOL_VISIBILITY_HIDDEN;
def->forceExport = f->forceExport;
f->flags |= WASM_SYMBOL_VISIBILITY_HIDDEN;
f->flags &= ~WASM_SYMBOL_EXPORTED;
f->forceExport = false;
out.functionSec->addFunction(func);
createCommandExportWrapper(f->getFunctionIndex(), def);
}
}
static void scanRelocations() {
for (ObjFile *file : symtab->objectFiles) {
LLVM_DEBUG(dbgs() << "scanRelocations: " << file->getName() << "\n");
for (InputChunk *chunk : file->functions)
scanRelocations(chunk);
for (InputChunk *chunk : file->segments)
scanRelocations(chunk);
for (auto &p : file->customSections)
scanRelocations(p);
}
}
void Writer::assignIndexes() {
// Seal the import section, since other index spaces such as function and
// global are effected by the number of imports.
out.importSec->seal();
for (InputFunction *func : symtab->syntheticFunctions)
out.functionSec->addFunction(func);
for (ObjFile *file : symtab->objectFiles) {
LLVM_DEBUG(dbgs() << "Functions: " << file->getName() << "\n");
for (InputFunction *func : file->functions)
out.functionSec->addFunction(func);
}
for (InputGlobal *global : symtab->syntheticGlobals)
out.globalSec->addGlobal(global);
for (ObjFile *file : symtab->objectFiles) {
LLVM_DEBUG(dbgs() << "Globals: " << file->getName() << "\n");
for (InputGlobal *global : file->globals)
out.globalSec->addGlobal(global);
}
for (ObjFile *file : symtab->objectFiles) {
LLVM_DEBUG(dbgs() << "Events: " << file->getName() << "\n");
for (InputEvent *event : file->events)
out.eventSec->addEvent(event);
}
out.globalSec->assignIndexes();
}
static StringRef getOutputDataSegmentName(StringRef name) {
// We only support one thread-local segment, so we must merge the segments
// despite --no-merge-data-segments.
// We also need to merge .tbss into .tdata so they share the same offsets.
if (name.startswith(".tdata") || name.startswith(".tbss"))
return ".tdata";
// With PIC code we currently only support a single data segment since
// we only have a single __memory_base to use as our base address.
if (config->isPic)
return ".data";
if (!config->mergeDataSegments)
return name;
if (name.startswith(".text."))
return ".text";
if (name.startswith(".data."))
return ".data";
if (name.startswith(".bss."))
return ".bss";
if (name.startswith(".rodata."))
return ".rodata";
return name;
}
void Writer::createOutputSegments() {
for (ObjFile *file : symtab->objectFiles) {
for (InputSegment *segment : file->segments) {
if (!segment->live)
continue;
StringRef name = getOutputDataSegmentName(segment->getName());
OutputSegment *&s = segmentMap[name];
if (s == nullptr) {
LLVM_DEBUG(dbgs() << "new segment: " << name << "\n");
s = make<OutputSegment>(name);
if (config->sharedMemory)
s->initFlags = WASM_SEGMENT_IS_PASSIVE;
// Exported memories are guaranteed to be zero-initialized, so no need
// to emit data segments for bss sections.
// TODO: consider initializing bss sections with memory.fill
// instructions when memory is imported and bulk-memory is available.
if (!config->importMemory && !config->relocatable &&
name.startswith(".bss"))
s->isBss = true;
segments.push_back(s);
}
s->addInputSegment(segment);
LLVM_DEBUG(dbgs() << "added data: " << name << ": " << s->size << "\n");
}
}
// Sort segments by type, placing .bss last
std::stable_sort(segments.begin(), segments.end(),
[](const OutputSegment *a, const OutputSegment *b) {
auto order = [](StringRef name) {
return StringSwitch<int>(name)
.StartsWith(".rodata", 0)
.StartsWith(".data", 1)
.StartsWith(".tdata", 2)
.StartsWith(".bss", 4)
.Default(3);
};
return order(a->name) < order(b->name);
});
for (size_t i = 0; i < segments.size(); ++i)
segments[i]->index = i;
}
static void createFunction(DefinedFunction *func, StringRef bodyContent) {
std::string functionBody;
{
raw_string_ostream os(functionBody);
writeUleb128(os, bodyContent.size(), "function size");
os << bodyContent;
}
ArrayRef<uint8_t> body = arrayRefFromStringRef(saver.save(functionBody));
cast<SyntheticFunction>(func->function)->setBody(body);
}
bool Writer::needsPassiveInitialization(const OutputSegment *segment) {
return segment->initFlags & WASM_SEGMENT_IS_PASSIVE &&
segment->name != ".tdata" && !segment->isBss;
}
bool Writer::hasPassiveInitializedSegments() {
return std::find_if(segments.begin(), segments.end(),
[this](const OutputSegment *s) {
return this->needsPassiveInitialization(s);
}) != segments.end();
}
void Writer::createInitMemoryFunction() {
LLVM_DEBUG(dbgs() << "createInitMemoryFunction\n");
assert(WasmSym::initMemoryFlag);
uint64_t flagAddress = WasmSym::initMemoryFlag->getVirtualAddress();
bool is64 = config->is64.getValueOr(false);
std::string bodyContent;
{
raw_string_ostream os(bodyContent);
// With PIC code we cache the flag address in local 0
if (config->isPic) {
writeUleb128(os, 1, "num local decls");
writeUleb128(os, 1, "local count");
writeU8(os, is64 ? WASM_TYPE_I64 : WASM_TYPE_I32, "address type");
writeU8(os, WASM_OPCODE_GLOBAL_GET, "GLOBAL_GET");
writeUleb128(os, WasmSym::memoryBase->getGlobalIndex(), "memory_base");
writePtrConst(os, flagAddress, is64, "flag address");
writeU8(os, WASM_OPCODE_I32_ADD, "add");
writeU8(os, WASM_OPCODE_LOCAL_SET, "local.set");
writeUleb128(os, 0, "local 0");
} else {
writeUleb128(os, 0, "num locals");
}
if (hasPassiveInitializedSegments()) {
// Initialize memory in a thread-safe manner. The thread that successfully
// increments the flag from 0 to 1 is is responsible for performing the
// memory initialization. Other threads go sleep on the flag until the
// first thread finishing initializing memory, increments the flag to 2,
// and wakes all the other threads. Once the flag has been set to 2,
// subsequently started threads will skip the sleep. All threads
// unconditionally drop their passive data segments once memory has been
// initialized. The generated code is as follows:
//
// (func $__wasm_init_memory
// (if
// (i32.atomic.rmw.cmpxchg align=2 offset=0
// (i32.const $__init_memory_flag)
// (i32.const 0)
// (i32.const 1)
// )
// (then
// (drop
// (i32.atomic.wait align=2 offset=0
// (i32.const $__init_memory_flag)
// (i32.const 1)
// (i32.const -1)
// )
// )
// )
// (else
// ( ... initialize data segments ... )
// (i32.atomic.store align=2 offset=0
// (i32.const $__init_memory_flag)
// (i32.const 2)
// )
// (drop
// (i32.atomic.notify align=2 offset=0
// (i32.const $__init_memory_flag)
// (i32.const -1u)
// )
// )
// )
// )
// ( ... drop data segments ... )
// )
//
// When we are building with PIC, calculate the flag location using:
//
// (global.get $__memory_base)
// (i32.const $__init_memory_flag)
// (i32.const 1)
auto writeGetFlagAddress = [&]() {
if (config->isPic) {
writeU8(os, WASM_OPCODE_LOCAL_GET, "local.get");
writeUleb128(os, 0, "local 0");
} else {
writePtrConst(os, flagAddress, is64, "flag address");
}
};
// Atomically check whether this is the main thread.
writeGetFlagAddress();
writeI32Const(os, 0, "expected flag value");
writeI32Const(os, 1, "flag value");
writeU8(os, WASM_OPCODE_ATOMICS_PREFIX, "atomics prefix");
writeUleb128(os, WASM_OPCODE_I32_RMW_CMPXCHG, "i32.atomic.rmw.cmpxchg");
writeMemArg(os, 2, 0);
writeU8(os, WASM_OPCODE_IF, "IF");
writeU8(os, WASM_TYPE_NORESULT, "blocktype");
// Did not increment 0, so wait for main thread to initialize memory
writeGetFlagAddress();
writeI32Const(os, 1, "expected flag value");
writeI64Const(os, -1, "timeout");
writeU8(os, WASM_OPCODE_ATOMICS_PREFIX, "atomics prefix");
writeUleb128(os, WASM_OPCODE_I32_ATOMIC_WAIT, "i32.atomic.wait");
writeMemArg(os, 2, 0);
writeU8(os, WASM_OPCODE_DROP, "drop");
writeU8(os, WASM_OPCODE_ELSE, "ELSE");
// Did increment 0, so conditionally initialize passive data segments
for (const OutputSegment *s : segments) {
if (needsPassiveInitialization(s)) {
// destination address
writePtrConst(os, s->startVA, is64, "destination address");
if (config->isPic) {
writeU8(os, WASM_OPCODE_GLOBAL_GET, "GLOBAL_GET");
writeUleb128(os, WasmSym::memoryBase->getGlobalIndex(),
"memory_base");
writeU8(os, WASM_OPCODE_I32_ADD, "i32.add");
}
// source segment offset
writeI32Const(os, 0, "segment offset");
// memory region size
writeI32Const(os, s->size, "memory region size");
// memory.init instruction
writeU8(os, WASM_OPCODE_MISC_PREFIX, "bulk-memory prefix");
writeUleb128(os, WASM_OPCODE_MEMORY_INIT, "memory.init");
writeUleb128(os, s->index, "segment index immediate");
writeU8(os, 0, "memory index immediate");
}
}
// Set flag to 2 to mark end of initialization
writeGetFlagAddress();
writeI32Const(os, 2, "flag value");
writeU8(os, WASM_OPCODE_ATOMICS_PREFIX, "atomics prefix");
writeUleb128(os, WASM_OPCODE_I32_ATOMIC_STORE, "i32.atomic.store");
writeMemArg(os, 2, 0);
// Notify any waiters that memory initialization is complete
writeGetFlagAddress();
writeI32Const(os, -1, "number of waiters");
writeU8(os, WASM_OPCODE_ATOMICS_PREFIX, "atomics prefix");
writeUleb128(os, WASM_OPCODE_ATOMIC_NOTIFY, "atomic.notify");
writeMemArg(os, 2, 0);
writeU8(os, WASM_OPCODE_DROP, "drop");
writeU8(os, WASM_OPCODE_END, "END");
// Unconditionally drop passive data segments
for (const OutputSegment *s : segments) {
if (needsPassiveInitialization(s)) {
// data.drop instruction
writeU8(os, WASM_OPCODE_MISC_PREFIX, "bulk-memory prefix");
writeUleb128(os, WASM_OPCODE_DATA_DROP, "data.drop");
writeUleb128(os, s->index, "segment index immediate");
}
}
}
writeU8(os, WASM_OPCODE_END, "END");
}
createFunction(WasmSym::initMemory, bodyContent);
}
// 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");
// 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);
}
// 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)
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) {
writeU8(os, WASM_OPCODE_CALL, "CALL");
writeUleb128(os, WasmSym::applyRelocs->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) {
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");
writeUleb128(os, i, "local index");
}
writeU8(os, WASM_OPCODE_CALL, "CALL");
writeUleb128(os, functionIndex, "function index");
// Call the function that calls the destructors.
if (DefinedFunction *callDtors = WasmSym::callDtors) {
writeU8(os, WASM_OPCODE_CALL, "CALL");
writeUleb128(os, callDtors->getFunctionIndex(), "function index");
}
// End the function, returning the return values from the user's code.
writeU8(os, WASM_OPCODE_END, "END");
}
createFunction(f, bodyContent);
}
void Writer::createInitTLSFunction() {
std::string bodyContent;
{
raw_string_ostream os(bodyContent);
OutputSegment *tlsSeg = nullptr;
for (auto *seg : segments) {
if (seg->name == ".tdata") {
tlsSeg = seg;
break;
}
}
writeUleb128(os, 0, "num locals");
if (tlsSeg) {
writeU8(os, WASM_OPCODE_LOCAL_GET, "local.get");
writeUleb128(os, 0, "local index");
writeU8(os, WASM_OPCODE_GLOBAL_SET, "global.set");
writeUleb128(os, WasmSym::tlsBase->getGlobalIndex(), "global index");
// FIXME(wvo): this local needs to be I64 in wasm64, or we need an extend op.
writeU8(os, WASM_OPCODE_LOCAL_GET, "local.get");
writeUleb128(os, 0, "local index");
writeI32Const(os, 0, "segment offset");
writeI32Const(os, tlsSeg->size, "memory region size");
writeU8(os, WASM_OPCODE_MISC_PREFIX, "bulk-memory prefix");
writeUleb128(os, WASM_OPCODE_MEMORY_INIT, "MEMORY.INIT");
writeUleb128(os, tlsSeg->index, "segment index immediate");
writeU8(os, 0, "memory index immediate");
}
writeU8(os, WASM_OPCODE_END, "end function");
}
createFunction(WasmSym::initTLS, bodyContent);
}
// Populate InitFunctions vector with init functions from all input objects.
// This is then used either when creating the output linking section or to
// synthesize the "__wasm_call_ctors" function.
void Writer::calculateInitFunctions() {
if (!config->relocatable && !WasmSym::callCtors->isLive())
return;
for (ObjFile *file : symtab->objectFiles) {
const WasmLinkingData &l = file->getWasmObj()->linkingData();
for (const WasmInitFunc &f : l.InitFunctions) {
FunctionSymbol *sym = file->getFunctionSymbol(f.Symbol);
// comdat exclusions can cause init functions be discarded.
if (sym->isDiscarded() || !sym->isLive())
continue;
if (sym->signature->Params.size() != 0)
error("constructor functions cannot take arguments: " + toString(*sym));
LLVM_DEBUG(dbgs() << "initFunctions: " << toString(*sym) << "\n");
initFunctions.emplace_back(WasmInitEntry{sym, f.Priority});
}
}
// Sort in order of priority (lowest first) so that they are called
// in the correct order.
llvm::stable_sort(initFunctions,
[](const WasmInitEntry &l, const WasmInitEntry &r) {
return l.priority < r.priority;
});
}
void Writer::createSyntheticSections() {
out.dylinkSec = make<DylinkSection>();
out.typeSec = make<TypeSection>();
out.importSec = make<ImportSection>();
out.functionSec = make<FunctionSection>();
out.tableSec = make<TableSection>();
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.producersSec = make<ProducersSection>();
out.targetFeaturesSec = make<TargetFeaturesSection>();
}
void Writer::run() {
if (config->relocatable || config->isPic)
config->globalBase = 0;
// For PIC code the table base is assigned dynamically by the loader.
// For non-PIC, we start at 1 so that accessing table index 0 always traps.
if (!config->isPic) {
config->tableBase = 1;
if (WasmSym::definedTableBase)
WasmSym::definedTableBase->setVirtualAddress(config->tableBase);
}
log("-- createOutputSegments");
createOutputSegments();
log("-- createSyntheticSections");
createSyntheticSections();
log("-- populateProducers");
populateProducers();
log("-- calculateImports");
calculateImports();
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("-- assignIndexes");
assignIndexes();
log("-- calculateInitFunctions");
calculateInitFunctions();
if (!config->relocatable) {
if (WasmSym::applyRelocs)
createApplyRelocationsFunction();
if (WasmSym::initMemory)
createInitMemoryFunction();
// 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 &&
!WasmSym::callCtors->isUsedInRegularObj &&
!WasmSym::callCtors->isExported()) {
log("-- createCommandExportWrappers");
createCommandExportWrappers();
}
}
if (WasmSym::initTLS && WasmSym::initTLS->isLive())
createInitTLSFunction();
if (errorCount())
return;
log("-- calculateTypes");
calculateTypes();
log("-- calculateExports");
calculateExports();
log("-- calculateCustomSections");
calculateCustomSections();
log("-- populateSymtab");
populateSymtab();
log("-- populateTargetFeatures");
populateTargetFeatures();
log("-- addSections");
addSections();
if (errorHandler().verbose) {
log("Defined Functions: " + Twine(out.functionSec->inputFunctions.size()));
log("Defined Globals : " + Twine(out.globalSec->numGlobals()));
log("Defined Events : " + Twine(out.eventSec->inputEvents.size()));
log("Function Imports : " +
Twine(out.importSec->getNumImportedFunctions()));
log("Global Imports : " + Twine(out.importSec->getNumImportedGlobals()));
log("Event Imports : " + Twine(out.importSec->getNumImportedEvents()));
for (ObjFile *file : symtab->objectFiles)
file->dumpInfo();
}
createHeader();
log("-- finalizeSections");
finalizeSections();
log("-- writeMapFile");
writeMapFile(outputSections);
log("-- openFile");
openFile();
if (errorCount())
return;
writeHeader();
log("-- writeSections");
writeSections();
if (errorCount())
return;
if (Error e = buffer->commit())
fatal("failed to write the output file: " + toString(std::move(e)));
}
// Open a result file.
void Writer::openFile() {
log("writing: " + config->outputFile);
Expected<std::unique_ptr<FileOutputBuffer>> bufferOrErr =
FileOutputBuffer::create(config->outputFile, fileSize,
FileOutputBuffer::F_executable);
if (!bufferOrErr)
error("failed to open " + config->outputFile + ": " +
toString(bufferOrErr.takeError()));
else
buffer = std::move(*bufferOrErr);
}
void Writer::createHeader() {
raw_string_ostream os(header);
writeBytes(os, WasmMagic, sizeof(WasmMagic), "wasm magic");
writeU32(os, WasmVersion, "wasm version");
os.flush();
fileSize += header.size();
}
void writeResult() { Writer().run(); }
} // namespace wasm
} // namespace lld
Reference in new issue View Git Blame Copy Permalink