mirror of
https://github.com/capstone-engine/llvm-capstone.git
synced 2024-12-28 02:37:37 +00:00
3646ee503d
Summary: There were a few issues with the previous setup: 1. The section sorting comparator used a declarative map of section names to determine the correct order, but it turns out we need to match on more than just names -- in particular, an upcoming diff will sort based on whether the S_ZERO_FILL flag is set. This diff changes the sorter to a more imperative but flexible form. 2. We were sorting OutputSections stored in a MapVector, which left the MapVector in an inconsistent state -- the wrong keys map to the wrong values! In practice, we weren't doing key lookups (only container iteration) after the sort, so this was fine, but it was still a dubious state of affairs. This diff copies the OutputSections to a vector before sorting them. 3. We were adding unneeded OutputSections to OutputSegments and then filtering them out later, which meant that we had to remember whether an OutputSegment was in a pre- or post-filtered state. This diff only adds the sections to the segments if they are needed. In addition to those major changes, two minor ones worth noting: 1. I renamed all OutputSection variable names to `osec`, to parallel `isec`. Previously we were using some inconsistent combination of `osec`, `os`, and `section`. 2. I added a check (and a test) for InputSections with names that clashed with those of our synthetic OutputSections. Reviewers: #lld-macho Subscribers: llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D81887
354 lines
12 KiB
C++
354 lines
12 KiB
C++
//===- SyntheticSections.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 "SyntheticSections.h"
|
|
#include "Config.h"
|
|
#include "ExportTrie.h"
|
|
#include "InputFiles.h"
|
|
#include "MachOStructs.h"
|
|
#include "OutputSegment.h"
|
|
#include "SymbolTable.h"
|
|
#include "Symbols.h"
|
|
#include "Writer.h"
|
|
|
|
#include "lld/Common/ErrorHandler.h"
|
|
#include "lld/Common/Memory.h"
|
|
#include "llvm/Support/EndianStream.h"
|
|
#include "llvm/Support/LEB128.h"
|
|
|
|
using namespace llvm;
|
|
using namespace llvm::MachO;
|
|
using namespace llvm::support;
|
|
using namespace llvm::support::endian;
|
|
|
|
namespace lld {
|
|
namespace macho {
|
|
|
|
SyntheticSection::SyntheticSection(const char *segname, const char *name)
|
|
: OutputSection(SyntheticKind, name), segname(segname) {
|
|
syntheticSections.push_back(this);
|
|
}
|
|
|
|
// dyld3's MachOLoaded::getSlide() assumes that the __TEXT segment starts
|
|
// from the beginning of the file (i.e. the header).
|
|
MachHeaderSection::MachHeaderSection()
|
|
: SyntheticSection(segment_names::text, section_names::header) {}
|
|
|
|
void MachHeaderSection::addLoadCommand(LoadCommand *lc) {
|
|
loadCommands.push_back(lc);
|
|
sizeOfCmds += lc->getSize();
|
|
}
|
|
|
|
uint64_t MachHeaderSection::getSize() const {
|
|
return sizeof(mach_header_64) + sizeOfCmds;
|
|
}
|
|
|
|
void MachHeaderSection::writeTo(uint8_t *buf) const {
|
|
auto *hdr = reinterpret_cast<mach_header_64 *>(buf);
|
|
hdr->magic = MH_MAGIC_64;
|
|
hdr->cputype = CPU_TYPE_X86_64;
|
|
hdr->cpusubtype = CPU_SUBTYPE_X86_64_ALL | CPU_SUBTYPE_LIB64;
|
|
hdr->filetype = config->outputType;
|
|
hdr->ncmds = loadCommands.size();
|
|
hdr->sizeofcmds = sizeOfCmds;
|
|
hdr->flags = MH_NOUNDEFS | MH_DYLDLINK | MH_TWOLEVEL;
|
|
if (config->outputType == MH_DYLIB && !config->hasReexports)
|
|
hdr->flags |= MH_NO_REEXPORTED_DYLIBS;
|
|
|
|
uint8_t *p = reinterpret_cast<uint8_t *>(hdr + 1);
|
|
for (LoadCommand *lc : loadCommands) {
|
|
lc->writeTo(p);
|
|
p += lc->getSize();
|
|
}
|
|
}
|
|
|
|
PageZeroSection::PageZeroSection()
|
|
: SyntheticSection(segment_names::pageZero, section_names::pageZero) {}
|
|
|
|
GotSection::GotSection()
|
|
: SyntheticSection(segment_names::dataConst, section_names::got) {
|
|
align = 8;
|
|
flags = S_NON_LAZY_SYMBOL_POINTERS;
|
|
|
|
// TODO: section_64::reserved1 should be an index into the indirect symbol
|
|
// table, which we do not currently emit
|
|
}
|
|
|
|
void GotSection::addEntry(Symbol &sym) {
|
|
if (entries.insert(&sym)) {
|
|
sym.gotIndex = entries.size() - 1;
|
|
}
|
|
}
|
|
|
|
void GotSection::writeTo(uint8_t *buf) const {
|
|
for (size_t i = 0, n = entries.size(); i < n; ++i)
|
|
if (auto *defined = dyn_cast<Defined>(entries[i]))
|
|
write64le(&buf[i * WordSize], defined->getVA());
|
|
}
|
|
|
|
BindingSection::BindingSection()
|
|
: SyntheticSection(segment_names::linkEdit, section_names::binding) {}
|
|
|
|
bool BindingSection::isNeeded() const { return in.got->isNeeded(); }
|
|
|
|
// Emit bind opcodes, which are a stream of byte-sized opcodes that dyld
|
|
// interprets to update a record with the following fields:
|
|
// * segment index (of the segment to write the symbol addresses to, typically
|
|
// the __DATA_CONST segment which contains the GOT)
|
|
// * offset within the segment, indicating the next location to write a binding
|
|
// * symbol type
|
|
// * symbol library ordinal (the index of its library's LC_LOAD_DYLIB command)
|
|
// * symbol name
|
|
// * addend
|
|
// When dyld sees BIND_OPCODE_DO_BIND, it uses the current record state to bind
|
|
// a symbol in the GOT, and increments the segment offset to point to the next
|
|
// entry. It does *not* clear the record state after doing the bind, so
|
|
// subsequent opcodes only need to encode the differences between bindings.
|
|
void BindingSection::finalizeContents() {
|
|
if (!isNeeded())
|
|
return;
|
|
|
|
raw_svector_ostream os{contents};
|
|
os << static_cast<uint8_t>(BIND_OPCODE_SET_SEGMENT_AND_OFFSET_ULEB |
|
|
in.got->parent->index);
|
|
encodeULEB128(in.got->getSegmentOffset(), os);
|
|
uint32_t entries_to_skip = 0;
|
|
for (const Symbol *sym : in.got->getEntries()) {
|
|
if (const auto *dysym = dyn_cast<DylibSymbol>(sym)) {
|
|
if (entries_to_skip != 0) {
|
|
os << static_cast<uint8_t>(BIND_OPCODE_ADD_ADDR_ULEB);
|
|
encodeULEB128(WordSize * entries_to_skip, os);
|
|
entries_to_skip = 0;
|
|
}
|
|
|
|
// TODO: Implement compact encoding -- we only need to encode the
|
|
// differences between consecutive symbol entries.
|
|
if (dysym->file->ordinal <= BIND_IMMEDIATE_MASK) {
|
|
os << static_cast<uint8_t>(BIND_OPCODE_SET_DYLIB_ORDINAL_IMM |
|
|
dysym->file->ordinal);
|
|
} else {
|
|
error("TODO: Support larger dylib symbol ordinals");
|
|
continue;
|
|
}
|
|
os << static_cast<uint8_t>(BIND_OPCODE_SET_SYMBOL_TRAILING_FLAGS_IMM)
|
|
<< dysym->getName() << '\0'
|
|
<< static_cast<uint8_t>(BIND_OPCODE_SET_TYPE_IMM | BIND_TYPE_POINTER)
|
|
<< static_cast<uint8_t>(BIND_OPCODE_DO_BIND);
|
|
} else {
|
|
// We have a defined symbol with a pre-populated address; skip over it.
|
|
++entries_to_skip;
|
|
}
|
|
}
|
|
|
|
os << static_cast<uint8_t>(BIND_OPCODE_DONE);
|
|
}
|
|
|
|
void BindingSection::writeTo(uint8_t *buf) const {
|
|
memcpy(buf, contents.data(), contents.size());
|
|
}
|
|
|
|
StubsSection::StubsSection()
|
|
: SyntheticSection(segment_names::text, "__stubs") {}
|
|
|
|
uint64_t StubsSection::getSize() const {
|
|
return entries.size() * target->stubSize;
|
|
}
|
|
|
|
void StubsSection::writeTo(uint8_t *buf) const {
|
|
size_t off = 0;
|
|
for (const DylibSymbol *sym : in.stubs->getEntries()) {
|
|
target->writeStub(buf + off, *sym);
|
|
off += target->stubSize;
|
|
}
|
|
}
|
|
|
|
void StubsSection::addEntry(DylibSymbol &sym) {
|
|
if (entries.insert(&sym))
|
|
sym.stubsIndex = entries.size() - 1;
|
|
}
|
|
|
|
StubHelperSection::StubHelperSection()
|
|
: SyntheticSection(segment_names::text, "__stub_helper") {}
|
|
|
|
uint64_t StubHelperSection::getSize() const {
|
|
return target->stubHelperHeaderSize +
|
|
in.stubs->getEntries().size() * target->stubHelperEntrySize;
|
|
}
|
|
|
|
bool StubHelperSection::isNeeded() const {
|
|
return !in.stubs->getEntries().empty();
|
|
}
|
|
|
|
void StubHelperSection::writeTo(uint8_t *buf) const {
|
|
target->writeStubHelperHeader(buf);
|
|
size_t off = target->stubHelperHeaderSize;
|
|
for (const DylibSymbol *sym : in.stubs->getEntries()) {
|
|
target->writeStubHelperEntry(buf + off, *sym, addr + off);
|
|
off += target->stubHelperEntrySize;
|
|
}
|
|
}
|
|
|
|
void StubHelperSection::setup() {
|
|
stubBinder = dyn_cast_or_null<DylibSymbol>(symtab->find("dyld_stub_binder"));
|
|
if (stubBinder == nullptr) {
|
|
error("symbol dyld_stub_binder not found (normally in libSystem.dylib). "
|
|
"Needed to perform lazy binding.");
|
|
return;
|
|
}
|
|
in.got->addEntry(*stubBinder);
|
|
|
|
inputSections.push_back(in.imageLoaderCache);
|
|
symtab->addDefined("__dyld_private", in.imageLoaderCache, 0);
|
|
}
|
|
|
|
ImageLoaderCacheSection::ImageLoaderCacheSection() {
|
|
segname = segment_names::data;
|
|
name = "__data";
|
|
uint8_t *arr = bAlloc.Allocate<uint8_t>(WordSize);
|
|
memset(arr, 0, WordSize);
|
|
data = {arr, WordSize};
|
|
}
|
|
|
|
LazyPointerSection::LazyPointerSection()
|
|
: SyntheticSection(segment_names::data, "__la_symbol_ptr") {
|
|
align = 8;
|
|
flags = S_LAZY_SYMBOL_POINTERS;
|
|
}
|
|
|
|
uint64_t LazyPointerSection::getSize() const {
|
|
return in.stubs->getEntries().size() * WordSize;
|
|
}
|
|
|
|
bool LazyPointerSection::isNeeded() const {
|
|
return !in.stubs->getEntries().empty();
|
|
}
|
|
|
|
void LazyPointerSection::writeTo(uint8_t *buf) const {
|
|
size_t off = 0;
|
|
for (const DylibSymbol *sym : in.stubs->getEntries()) {
|
|
uint64_t stubHelperOffset = target->stubHelperHeaderSize +
|
|
sym->stubsIndex * target->stubHelperEntrySize;
|
|
write64le(buf + off, in.stubHelper->addr + stubHelperOffset);
|
|
off += WordSize;
|
|
}
|
|
}
|
|
|
|
LazyBindingSection::LazyBindingSection()
|
|
: SyntheticSection(segment_names::linkEdit, section_names::lazyBinding) {}
|
|
|
|
bool LazyBindingSection::isNeeded() const { return in.stubs->isNeeded(); }
|
|
|
|
void LazyBindingSection::finalizeContents() {
|
|
// TODO: Just precompute output size here instead of writing to a temporary
|
|
// buffer
|
|
for (DylibSymbol *sym : in.stubs->getEntries())
|
|
sym->lazyBindOffset = encode(*sym);
|
|
}
|
|
|
|
void LazyBindingSection::writeTo(uint8_t *buf) const {
|
|
memcpy(buf, contents.data(), contents.size());
|
|
}
|
|
|
|
// Unlike the non-lazy binding section, the bind opcodes in this section aren't
|
|
// interpreted all at once. Rather, dyld will start interpreting opcodes at a
|
|
// given offset, typically only binding a single symbol before it finds a
|
|
// BIND_OPCODE_DONE terminator. As such, unlike in the non-lazy-binding case,
|
|
// we cannot encode just the differences between symbols; we have to emit the
|
|
// complete bind information for each symbol.
|
|
uint32_t LazyBindingSection::encode(const DylibSymbol &sym) {
|
|
uint32_t opstreamOffset = contents.size();
|
|
OutputSegment *dataSeg = in.lazyPointers->parent;
|
|
os << static_cast<uint8_t>(BIND_OPCODE_SET_SEGMENT_AND_OFFSET_ULEB |
|
|
dataSeg->index);
|
|
uint64_t offset = in.lazyPointers->addr - dataSeg->firstSection()->addr +
|
|
sym.stubsIndex * WordSize;
|
|
encodeULEB128(offset, os);
|
|
if (sym.file->ordinal <= BIND_IMMEDIATE_MASK)
|
|
os << static_cast<uint8_t>(BIND_OPCODE_SET_DYLIB_ORDINAL_IMM |
|
|
sym.file->ordinal);
|
|
else
|
|
fatal("TODO: Support larger dylib symbol ordinals");
|
|
|
|
os << static_cast<uint8_t>(BIND_OPCODE_SET_SYMBOL_TRAILING_FLAGS_IMM)
|
|
<< sym.getName() << '\0' << static_cast<uint8_t>(BIND_OPCODE_DO_BIND)
|
|
<< static_cast<uint8_t>(BIND_OPCODE_DONE);
|
|
return opstreamOffset;
|
|
}
|
|
|
|
ExportSection::ExportSection()
|
|
: SyntheticSection(segment_names::linkEdit, section_names::export_) {}
|
|
|
|
void ExportSection::finalizeContents() {
|
|
// TODO: We should check symbol visibility.
|
|
for (const Symbol *sym : symtab->getSymbols())
|
|
if (auto *defined = dyn_cast<Defined>(sym))
|
|
trieBuilder.addSymbol(*defined);
|
|
size = trieBuilder.build();
|
|
}
|
|
|
|
void ExportSection::writeTo(uint8_t *buf) const { trieBuilder.writeTo(buf); }
|
|
|
|
SymtabSection::SymtabSection(StringTableSection &stringTableSection)
|
|
: SyntheticSection(segment_names::linkEdit, section_names::symbolTable),
|
|
stringTableSection(stringTableSection) {
|
|
// TODO: When we introduce the SyntheticSections superclass, we should make
|
|
// all synthetic sections aligned to WordSize by default.
|
|
align = WordSize;
|
|
}
|
|
|
|
uint64_t SymtabSection::getSize() const {
|
|
return symbols.size() * sizeof(structs::nlist_64);
|
|
}
|
|
|
|
void SymtabSection::finalizeContents() {
|
|
// TODO support other symbol types
|
|
for (Symbol *sym : symtab->getSymbols())
|
|
if (isa<Defined>(sym))
|
|
symbols.push_back({sym, stringTableSection.addString(sym->getName())});
|
|
}
|
|
|
|
void SymtabSection::writeTo(uint8_t *buf) const {
|
|
auto *nList = reinterpret_cast<structs::nlist_64 *>(buf);
|
|
for (const SymtabEntry &entry : symbols) {
|
|
nList->n_strx = entry.strx;
|
|
// TODO support other symbol types
|
|
// TODO populate n_desc
|
|
if (auto *defined = dyn_cast<Defined>(entry.sym)) {
|
|
nList->n_type = N_EXT | N_SECT;
|
|
nList->n_sect = defined->isec->parent->index;
|
|
// For the N_SECT symbol type, n_value is the address of the symbol
|
|
nList->n_value = defined->value + defined->isec->getVA();
|
|
}
|
|
++nList;
|
|
}
|
|
}
|
|
|
|
StringTableSection::StringTableSection()
|
|
: SyntheticSection(segment_names::linkEdit, section_names::stringTable) {}
|
|
|
|
uint32_t StringTableSection::addString(StringRef str) {
|
|
uint32_t strx = size;
|
|
strings.push_back(str);
|
|
size += str.size() + 1; // account for null terminator
|
|
return strx;
|
|
}
|
|
|
|
void StringTableSection::writeTo(uint8_t *buf) const {
|
|
uint32_t off = 0;
|
|
for (StringRef str : strings) {
|
|
memcpy(buf + off, str.data(), str.size());
|
|
off += str.size() + 1; // account for null terminator
|
|
}
|
|
}
|
|
|
|
InStruct in;
|
|
std::vector<SyntheticSection *> syntheticSections;
|
|
|
|
} // namespace macho
|
|
} // namespace lld
|