llvm-project/bolt/lib/Rewrite/JITLinkLinker.cpp
Job Noorman 475a93a07a [BOLT] Calculate output values using BOLTLinker
BOLT uses `MCAsmLayout` to calculate the output values of functions and
basic blocks. This means output values are calculated based on a
pre-linking state and any changes to symbol values during linking will
cause incorrect values to be used.

This issue can be triggered by enabling linker relaxation on RISC-V.
Since linker relaxation can remove instructions, symbol values may
change. This causes, among other things, the symbol table created by
BOLT in the output executable to be incorrect.

This patch solves this issue by using `BOLTLinker` to get symbol values
instead of `MCAsmLayout`. This way, output values are calculated based
on a post-linking state. To make sure the linker can update all
necessary symbols, this patch also makes sure all these symbols are not
marked as temporary so that they end-up in the object file's symbol
table.

Note that this patch only deals with symbols of binary functions
(`BinaryFunction::updateOutputValues`). The technique described above
turned out to be too expensive for basic block symbols so those are
handled differently in D155604.

Reviewed By: maksfb

Differential Revision: https://reviews.llvm.org/D154604
2023-08-28 10:13:07 +02:00

208 lines
6.8 KiB
C++

//===- bolt/Rewrite/JITLinkLinker.cpp - BOLTLinker using JITLink ----------===//
//
// 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 "bolt/Rewrite/JITLinkLinker.h"
#include "bolt/Core/BinaryData.h"
#include "bolt/Rewrite/RewriteInstance.h"
#include "llvm/ExecutionEngine/JITLink/JITLink.h"
#include "llvm/ExecutionEngine/Orc/Shared/ExecutorAddress.h"
#include "llvm/ExecutionEngine/Orc/Shared/ExecutorSymbolDef.h"
#include "llvm/Support/Debug.h"
#define DEBUG_TYPE "bolt"
namespace llvm {
namespace bolt {
namespace {
bool hasSymbols(const jitlink::Block &B) {
return llvm::any_of(B.getSection().symbols(),
[&B](const auto &S) { return &S->getBlock() == &B; });
}
/// Liveness in JITLink is based on symbols so sections that do not contain
/// any symbols will always be pruned. This pass adds anonymous symbols to
/// needed sections to prevent pruning.
Error markSectionsLive(jitlink::LinkGraph &G) {
for (auto &Section : G.sections()) {
// We only need allocatable sections.
if (Section.getMemLifetimePolicy() == orc::MemLifetimePolicy::NoAlloc)
continue;
// Skip empty sections.
if (JITLinkLinker::sectionSize(Section) == 0)
continue;
for (auto *Block : Section.blocks()) {
// No need to add symbols if it already has some.
if (hasSymbols(*Block))
continue;
G.addAnonymousSymbol(*Block, /*Offset=*/0, /*Size=*/0,
/*IsCallable=*/false, /*IsLive=*/true);
}
}
return jitlink::markAllSymbolsLive(G);
}
void reassignSectionAddress(jitlink::LinkGraph &LG,
const BinarySection &BinSection, uint64_t Address) {
auto *JLSection = LG.findSectionByName(BinSection.getSectionID());
assert(JLSection && "cannot find section in LinkGraph");
auto BlockAddress = Address;
for (auto *Block : JITLinkLinker::orderedBlocks(*JLSection)) {
// FIXME it would seem to make sense to align here. However, in
// non-relocation mode, we simply use the original address of functions
// which might not be aligned with the minimum alignment used by
// BinaryFunction (2). Example failing test when aligning:
// bolt/test/X86/addr32.s
Block->setAddress(orc::ExecutorAddr(BlockAddress));
BlockAddress += Block->getSize();
}
}
} // anonymous namespace
struct JITLinkLinker::Context : jitlink::JITLinkContext {
JITLinkLinker &Linker;
JITLinkLinker::SectionsMapper MapSections;
Context(JITLinkLinker &Linker, JITLinkLinker::SectionsMapper MapSections)
: JITLinkContext(&Linker.Dylib), Linker(Linker),
MapSections(MapSections) {}
jitlink::JITLinkMemoryManager &getMemoryManager() override {
return *Linker.MM;
}
bool shouldAddDefaultTargetPasses(const Triple &TT) const override {
// The default passes manipulate DWARF sections in a way incompatible with
// BOLT.
// TODO check if we can actually use these passes to remove some of the
// DWARF manipulation done in BOLT.
return false;
}
Error modifyPassConfig(jitlink::LinkGraph &G,
jitlink::PassConfiguration &Config) override {
Config.PrePrunePasses.push_back(markSectionsLive);
return Error::success();
}
void notifyFailed(Error Err) override {
errs() << "BOLT-ERROR: JITLink failed: " << Err << '\n';
exit(1);
}
void
lookup(const LookupMap &Symbols,
std::unique_ptr<jitlink::JITLinkAsyncLookupContinuation> LC) override {
jitlink::AsyncLookupResult AllResults;
for (const auto &Symbol : Symbols) {
std::string SymName = Symbol.first.str();
LLVM_DEBUG(dbgs() << "BOLT: looking for " << SymName << "\n");
if (auto Address = Linker.lookupSymbol(SymName)) {
LLVM_DEBUG(dbgs() << "Resolved to address 0x"
<< Twine::utohexstr(*Address) << "\n");
AllResults[Symbol.first] = orc::ExecutorSymbolDef(
orc::ExecutorAddr(*Address), JITSymbolFlags());
continue;
}
if (const BinaryData *I = Linker.BC.getBinaryDataByName(SymName)) {
uint64_t Address = I->isMoved() && !I->isJumpTable()
? I->getOutputAddress()
: I->getAddress();
LLVM_DEBUG(dbgs() << "Resolved to address 0x"
<< Twine::utohexstr(Address) << "\n");
AllResults[Symbol.first] = orc::ExecutorSymbolDef(
orc::ExecutorAddr(Address), JITSymbolFlags());
continue;
}
LLVM_DEBUG(dbgs() << "Resolved to address 0x0\n");
AllResults[Symbol.first] =
orc::ExecutorSymbolDef(orc::ExecutorAddr(0), JITSymbolFlags());
}
LC->run(std::move(AllResults));
}
Error notifyResolved(jitlink::LinkGraph &G) override {
MapSections([&G](const BinarySection &Section, uint64_t Address) {
reassignSectionAddress(G, Section, Address);
});
for (auto *Symbol : G.defined_symbols()) {
SymbolInfo Info{Symbol->getAddress().getValue(), Symbol->getSize()};
Linker.Symtab.insert({Symbol->getName().str(), Info});
}
return Error::success();
}
void notifyFinalized(
jitlink::JITLinkMemoryManager::FinalizedAlloc Alloc) override {
Linker.Allocs.push_back(std::move(Alloc));
++Linker.MM->ObjectsLoaded;
}
};
JITLinkLinker::JITLinkLinker(BinaryContext &BC,
std::unique_ptr<ExecutableFileMemoryManager> MM)
: BC(BC), MM(std::move(MM)) {}
JITLinkLinker::~JITLinkLinker() { cantFail(MM->deallocate(std::move(Allocs))); }
void JITLinkLinker::loadObject(MemoryBufferRef Obj,
SectionsMapper MapSections) {
auto LG = jitlink::createLinkGraphFromObject(Obj);
if (auto E = LG.takeError()) {
errs() << "BOLT-ERROR: JITLink failed: " << E << '\n';
exit(1);
}
auto Ctx = std::make_unique<Context>(*this, MapSections);
jitlink::link(std::move(*LG), std::move(Ctx));
}
std::optional<JITLinkLinker::SymbolInfo>
JITLinkLinker::lookupSymbolInfo(StringRef Name) const {
auto It = Symtab.find(Name.data());
if (It == Symtab.end())
return std::nullopt;
return It->second;
}
SmallVector<jitlink::Block *, 2>
JITLinkLinker::orderedBlocks(const jitlink::Section &Section) {
SmallVector<jitlink::Block *, 2> Blocks(Section.blocks());
llvm::sort(Blocks, [](const auto *LHS, const auto *RHS) {
return LHS->getAddress() < RHS->getAddress();
});
return Blocks;
}
size_t JITLinkLinker::sectionSize(const jitlink::Section &Section) {
size_t Size = 0;
for (const auto *Block : orderedBlocks(Section)) {
Size = jitlink::alignToBlock(Size, *Block);
Size += Block->getSize();
}
return Size;
}
} // namespace bolt
} // namespace llvm