Files
clang-p2996/llvm/lib/MC/MCWinCOFFStreamer.cpp
Daniel Paoliello 5ee0a71df9 [aarch64][win] Add support for import call optimization (equivalent to MSVC /d2ImportCallOptimization) (#121516)
This change implements import call optimization for AArch64 Windows
(equivalent to the undocumented MSVC `/d2ImportCallOptimization` flag).

Import call optimization adds additional data to the binary which can be
used by the Windows kernel loader to rewrite indirect calls to imported
functions as direct calls. It uses the same [Dynamic Value Relocation
Table mechanism that was leveraged on x64 to implement
`/d2GuardRetpoline`](https://techcommunity.microsoft.com/blog/windowsosplatform/mitigating-spectre-variant-2-with-retpoline-on-windows/295618).

The change to the obj file is to add a new `.impcall` section with the
following layout:
```cpp
  // Per section that contains calls to imported functions:
  //  uint32_t SectionSize: Size in bytes for information in this section.
  //  uint32_t Section Number
  //  Per call to imported function in section:
  //    uint32_t Kind: the kind of imported function.
  //    uint32_t BranchOffset: the offset of the branch instruction in its
  //                            parent section.
  //    uint32_t TargetSymbolId: the symbol id of the called function.
```

NOTE: If the import call optimization feature is enabled, then the
`.impcall` section must be emitted, even if there are no calls to
imported functions.

The implementation is split across a few parts of LLVM:
* During AArch64 instruction selection, the `GlobalValue` for each call
to a global is recorded into the Extra Information for that node.
* During lowering to machine instructions, the called global value for
each call is noted in its containing `MachineFunction`.
* During AArch64 asm printing, if the import call optimization feature
is enabled:
- A (new) `.impcall` directive is emitted for each call to an imported
function.
- The `.impcall` section is emitted with its magic header (but is not
filled in).
* During COFF object writing, the `.impcall` section is filled in based
on each `.impcall` directive that were encountered.

The `.impcall` section can only be filled in when we are writing the
COFF object as it requires the actual section numbers, which are only
assigned at that point (i.e., they don't exist during asm printing).

I had tried to avoid using the Extra Information during instruction
selection and instead implement this either purely during asm printing
or in a `MachineFunctionPass` (as suggested in [on the
forums](https://discourse.llvm.org/t/design-gathering-locations-of-instructions-to-emit-into-a-section/83729/3))
but this was not possible due to how loading and calling an imported
function works on AArch64. Specifically, they are emitted as `ADRP` +
`LDR` (to load the symbol) then a `BR` (to do the call), so at the point
when we have machine instructions, we would have to work backwards
through the instructions to discover what is being called. An initial
prototype did work by inspecting instructions; however, it didn't
correctly handle the case where the same function was called twice in a
row, which caused LLVM to elide the `ADRP` + `LDR` and reuse the
previously loaded address. Worse than that, sometimes for the
double-call case LLVM decided to spill the loaded address to the stack
and then reload it before making the second call. So, instead of trying
to implement logic to discover where the value in a register came from,
I instead recorded the symbol being called at the last place where it
was easy to do: instruction selection.
2025-01-11 21:30:17 -08:00

510 lines
17 KiB
C++

//===- llvm/MC/MCWinCOFFStreamer.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
//
//===----------------------------------------------------------------------===//
//
// This file contains an implementation of a Windows COFF object file streamer.
//
//===----------------------------------------------------------------------===//
#include "llvm/MC/MCWinCOFFStreamer.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Twine.h"
#include "llvm/BinaryFormat/COFF.h"
#include "llvm/MC/MCAsmBackend.h"
#include "llvm/MC/MCAssembler.h"
#include "llvm/MC/MCCodeEmitter.h"
#include "llvm/MC/MCCodeView.h"
#include "llvm/MC/MCContext.h"
#include "llvm/MC/MCExpr.h"
#include "llvm/MC/MCFixup.h"
#include "llvm/MC/MCFragment.h"
#include "llvm/MC/MCObjectFileInfo.h"
#include "llvm/MC/MCObjectStreamer.h"
#include "llvm/MC/MCObjectWriter.h"
#include "llvm/MC/MCSectionCOFF.h"
#include "llvm/MC/MCSymbolCOFF.h"
#include "llvm/MC/MCTargetOptions.h"
#include "llvm/MC/MCValue.h"
#include "llvm/MC/MCWinCOFFObjectWriter.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/SMLoc.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/TargetParser/Triple.h"
#include <algorithm>
#include <cstdint>
using namespace llvm;
#define DEBUG_TYPE "WinCOFFStreamer"
/// MCExpr that represents the physical number for the sections that contains
/// a symbol.
class MCCOFFSectionNumberTargetExpr final : public MCTargetExpr {
const MCSymbol &SectionSymbol;
const WinCOFFObjectWriter &Writer;
MCCOFFSectionNumberTargetExpr(const MCSymbol &SectionSymbol_,
const WinCOFFObjectWriter &Writer_)
: SectionSymbol(SectionSymbol_), Writer(Writer_) {}
public:
static MCCOFFSectionNumberTargetExpr *
create(const MCSymbol &SectionSymbol, const WinCOFFObjectWriter &Writer,
MCContext &Ctx) {
return new (Ctx) MCCOFFSectionNumberTargetExpr(SectionSymbol, Writer);
}
void printImpl(raw_ostream &OS, const MCAsmInfo *MAI) const override {
OS << ":secnum:";
SectionSymbol.print(OS, MAI);
}
bool evaluateAsRelocatableImpl(MCValue &Res, const MCAssembler *Asm,
const MCFixup *Fixup) const override {
auto sectionNumber = Writer.getSectionNumber(SectionSymbol.getSection());
assert(sectionNumber != 0 &&
"Containing section was not assigned a number");
Res = MCValue::get(sectionNumber);
return true;
}
void visitUsedExpr(MCStreamer &Streamer) const override {
// Contains no sub-expressions.
}
MCFragment *findAssociatedFragment() const override {
return SectionSymbol.getFragment();
}
void fixELFSymbolsInTLSFixups(MCAssembler &) const override {
llvm_unreachable("Not supported for ELF");
}
};
/// MCExpr that represents the offset to a symbol from the beginning of its
/// section.
class MCCOFFSectionOffsetTargetExpr final : public MCTargetExpr {
const MCSymbol &Symbol;
MCCOFFSectionOffsetTargetExpr(const MCSymbol &Symbol_) : Symbol(Symbol_) {}
public:
static MCCOFFSectionOffsetTargetExpr *create(const MCSymbol &Symbol,
MCContext &Ctx) {
return new (Ctx) MCCOFFSectionOffsetTargetExpr(Symbol);
}
void printImpl(raw_ostream &OS, const MCAsmInfo *MAI) const override {
OS << ":secoffset:";
Symbol.print(OS, MAI);
}
bool evaluateAsRelocatableImpl(MCValue &Res, const MCAssembler *Asm,
const MCFixup *Fixup) const override {
uint64_t CallsiteOffset = 0;
if (!Asm->getSymbolOffset(Symbol, CallsiteOffset)) {
return true;
}
Res = MCValue::get(CallsiteOffset);
return true;
}
void visitUsedExpr(MCStreamer &Streamer) const override {
// Contains no sub-expressions.
}
MCFragment *findAssociatedFragment() const override {
return Symbol.getFragment();
}
void fixELFSymbolsInTLSFixups(MCAssembler &) const override {
llvm_unreachable("Not supported for ELF");
}
};
MCWinCOFFStreamer::MCWinCOFFStreamer(MCContext &Context,
std::unique_ptr<MCAsmBackend> MAB,
std::unique_ptr<MCCodeEmitter> CE,
std::unique_ptr<MCObjectWriter> OW)
: MCObjectStreamer(Context, std::move(MAB), std::move(OW), std::move(CE)),
CurSymbol(nullptr) {
auto *TO = Context.getTargetOptions();
if (TO && TO->MCIncrementalLinkerCompatible)
getWriter().setIncrementalLinkerCompatible(true);
}
WinCOFFObjectWriter &MCWinCOFFStreamer::getWriter() {
return static_cast<WinCOFFObjectWriter &>(getAssembler().getWriter());
}
void MCWinCOFFStreamer::emitInstToData(const MCInst &Inst,
const MCSubtargetInfo &STI) {
MCDataFragment *DF = getOrCreateDataFragment();
SmallVector<MCFixup, 4> Fixups;
SmallString<256> Code;
getAssembler().getEmitter().encodeInstruction(Inst, Code, Fixups, STI);
// Add the fixups and data.
for (unsigned i = 0, e = Fixups.size(); i != e; ++i) {
Fixups[i].setOffset(Fixups[i].getOffset() + DF->getContents().size());
DF->getFixups().push_back(Fixups[i]);
}
DF->setHasInstructions(STI);
DF->appendContents(Code);
}
void MCWinCOFFStreamer::initSections(bool NoExecStack,
const MCSubtargetInfo &STI) {
// FIXME: this is identical to the ELF one.
// This emulates the same behavior of GNU as. This makes it easier
// to compare the output as the major sections are in the same order.
switchSection(getContext().getObjectFileInfo()->getTextSection());
emitCodeAlignment(Align(4), &STI);
switchSection(getContext().getObjectFileInfo()->getDataSection());
emitCodeAlignment(Align(4), &STI);
switchSection(getContext().getObjectFileInfo()->getBSSSection());
emitCodeAlignment(Align(4), &STI);
switchSection(getContext().getObjectFileInfo()->getTextSection());
}
void MCWinCOFFStreamer::changeSection(MCSection *Section, uint32_t Subsection) {
changeSectionImpl(Section, Subsection);
// Ensure that the first and the second symbols relative to the section are
// the section symbol and the COMDAT symbol.
getAssembler().registerSymbol(*Section->getBeginSymbol());
if (auto *Sym = cast<MCSectionCOFF>(Section)->getCOMDATSymbol())
getAssembler().registerSymbol(*Sym);
}
void MCWinCOFFStreamer::emitLabel(MCSymbol *S, SMLoc Loc) {
auto *Symbol = cast<MCSymbolCOFF>(S);
MCObjectStreamer::emitLabel(Symbol, Loc);
}
void MCWinCOFFStreamer::emitAssemblerFlag(MCAssemblerFlag Flag) {
// Let the target do whatever target specific stuff it needs to do.
getAssembler().getBackend().handleAssemblerFlag(Flag);
switch (Flag) {
// None of these require COFF specific handling.
case MCAF_SyntaxUnified:
case MCAF_Code16:
case MCAF_Code32:
case MCAF_Code64:
break;
case MCAF_SubsectionsViaSymbols:
llvm_unreachable("COFF doesn't support .subsections_via_symbols");
}
}
void MCWinCOFFStreamer::emitThumbFunc(MCSymbol *Func) {
llvm_unreachable("not implemented");
}
bool MCWinCOFFStreamer::emitSymbolAttribute(MCSymbol *S,
MCSymbolAttr Attribute) {
auto *Symbol = cast<MCSymbolCOFF>(S);
getAssembler().registerSymbol(*Symbol);
switch (Attribute) {
default: return false;
case MCSA_WeakReference:
case MCSA_Weak:
Symbol->setWeakExternalCharacteristics(COFF::IMAGE_WEAK_EXTERN_SEARCH_ALIAS);
Symbol->setExternal(true);
break;
case MCSA_WeakAntiDep:
Symbol->setWeakExternalCharacteristics(COFF::IMAGE_WEAK_EXTERN_ANTI_DEPENDENCY);
Symbol->setExternal(true);
Symbol->setIsWeakExternal(true);
break;
case MCSA_Global:
Symbol->setExternal(true);
break;
case MCSA_AltEntry:
llvm_unreachable("COFF doesn't support the .alt_entry attribute");
}
return true;
}
void MCWinCOFFStreamer::emitSymbolDesc(MCSymbol *Symbol, unsigned DescValue) {
llvm_unreachable("not implemented");
}
void MCWinCOFFStreamer::beginCOFFSymbolDef(MCSymbol const *S) {
auto *Symbol = cast<MCSymbolCOFF>(S);
if (CurSymbol)
Error("starting a new symbol definition without completing the "
"previous one");
CurSymbol = Symbol;
}
void MCWinCOFFStreamer::emitCOFFSymbolStorageClass(int StorageClass) {
if (!CurSymbol) {
Error("storage class specified outside of symbol definition");
return;
}
if (StorageClass & ~COFF::SSC_Invalid) {
Error("storage class value '" + Twine(StorageClass) +
"' out of range");
return;
}
getAssembler().registerSymbol(*CurSymbol);
cast<MCSymbolCOFF>(CurSymbol)->setClass((uint16_t)StorageClass);
}
void MCWinCOFFStreamer::emitCOFFSymbolType(int Type) {
if (!CurSymbol) {
Error("symbol type specified outside of a symbol definition");
return;
}
if (Type & ~0xffff) {
Error("type value '" + Twine(Type) + "' out of range");
return;
}
getAssembler().registerSymbol(*CurSymbol);
cast<MCSymbolCOFF>(CurSymbol)->setType((uint16_t)Type);
}
void MCWinCOFFStreamer::endCOFFSymbolDef() {
if (!CurSymbol)
Error("ending symbol definition without starting one");
CurSymbol = nullptr;
}
void MCWinCOFFStreamer::emitCOFFSafeSEH(MCSymbol const *Symbol) {
// SafeSEH is a feature specific to 32-bit x86. It does not exist (and is
// unnecessary) on all platforms which use table-based exception dispatch.
if (getContext().getTargetTriple().getArch() != Triple::x86)
return;
const MCSymbolCOFF *CSymbol = cast<MCSymbolCOFF>(Symbol);
if (CSymbol->isSafeSEH())
return;
MCSection *SXData = getContext().getObjectFileInfo()->getSXDataSection();
changeSection(SXData);
SXData->ensureMinAlignment(Align(4));
insert(getContext().allocFragment<MCSymbolIdFragment>(Symbol));
getAssembler().registerSymbol(*Symbol);
CSymbol->setIsSafeSEH();
// The Microsoft linker requires that the symbol type of a handler be
// function. Go ahead and oblige it here.
CSymbol->setType(COFF::IMAGE_SYM_DTYPE_FUNCTION
<< COFF::SCT_COMPLEX_TYPE_SHIFT);
}
void MCWinCOFFStreamer::emitCOFFSymbolIndex(MCSymbol const *Symbol) {
MCSection *Sec = getCurrentSectionOnly();
Sec->ensureMinAlignment(Align(4));
insert(getContext().allocFragment<MCSymbolIdFragment>(Symbol));
getAssembler().registerSymbol(*Symbol);
}
void MCWinCOFFStreamer::emitCOFFSectionIndex(const MCSymbol *Symbol) {
visitUsedSymbol(*Symbol);
MCDataFragment *DF = getOrCreateDataFragment();
const MCSymbolRefExpr *SRE = MCSymbolRefExpr::create(Symbol, getContext());
MCFixup Fixup = MCFixup::create(DF->getContents().size(), SRE, FK_SecRel_2);
DF->getFixups().push_back(Fixup);
DF->appendContents(2, 0);
}
void MCWinCOFFStreamer::emitCOFFSecRel32(const MCSymbol *Symbol,
uint64_t Offset) {
visitUsedSymbol(*Symbol);
MCDataFragment *DF = getOrCreateDataFragment();
// Create Symbol A for the relocation relative reference.
const MCExpr *MCE = MCSymbolRefExpr::create(Symbol, getContext());
// Add the constant offset, if given.
if (Offset)
MCE = MCBinaryExpr::createAdd(
MCE, MCConstantExpr::create(Offset, getContext()), getContext());
// Build the secrel32 relocation.
MCFixup Fixup = MCFixup::create(DF->getContents().size(), MCE, FK_SecRel_4);
// Record the relocation.
DF->getFixups().push_back(Fixup);
// Emit 4 bytes (zeros) to the object file.
DF->appendContents(4, 0);
}
void MCWinCOFFStreamer::emitCOFFImgRel32(const MCSymbol *Symbol,
int64_t Offset) {
visitUsedSymbol(*Symbol);
MCDataFragment *DF = getOrCreateDataFragment();
// Create Symbol A for the relocation relative reference.
const MCExpr *MCE = MCSymbolRefExpr::create(
Symbol, MCSymbolRefExpr::VK_COFF_IMGREL32, getContext());
// Add the constant offset, if given.
if (Offset)
MCE = MCBinaryExpr::createAdd(
MCE, MCConstantExpr::create(Offset, getContext()), getContext());
// Build the imgrel relocation.
MCFixup Fixup = MCFixup::create(DF->getContents().size(), MCE, FK_Data_4);
// Record the relocation.
DF->getFixups().push_back(Fixup);
// Emit 4 bytes (zeros) to the object file.
DF->appendContents(4, 0);
}
void MCWinCOFFStreamer::emitCOFFSecNumber(MCSymbol const *Symbol) {
visitUsedSymbol(*Symbol);
MCDataFragment *DF = getOrCreateDataFragment();
// Create Symbol for section number.
const MCExpr *MCE = MCCOFFSectionNumberTargetExpr::create(
*Symbol, this->getWriter(), getContext());
// Build the relocation.
MCFixup Fixup = MCFixup::create(DF->getContents().size(), MCE, FK_Data_4);
// Record the relocation.
DF->getFixups().push_back(Fixup);
// Emit 4 bytes (zeros) to the object file.
DF->appendContents(4, 0);
}
void MCWinCOFFStreamer::emitCOFFSecOffset(MCSymbol const *Symbol) {
visitUsedSymbol(*Symbol);
MCDataFragment *DF = getOrCreateDataFragment();
// Create Symbol for section offset.
const MCExpr *MCE =
MCCOFFSectionOffsetTargetExpr::create(*Symbol, getContext());
// Build the relocation.
MCFixup Fixup = MCFixup::create(DF->getContents().size(), MCE, FK_Data_4);
// Record the relocation.
DF->getFixups().push_back(Fixup);
// Emit 4 bytes (zeros) to the object file.
DF->appendContents(4, 0);
}
void MCWinCOFFStreamer::emitCommonSymbol(MCSymbol *S, uint64_t Size,
Align ByteAlignment) {
auto *Symbol = cast<MCSymbolCOFF>(S);
const Triple &T = getContext().getTargetTriple();
if (T.isWindowsMSVCEnvironment()) {
if (ByteAlignment > 32)
report_fatal_error("alignment is limited to 32-bytes");
// Round size up to alignment so that we will honor the alignment request.
Size = std::max(Size, ByteAlignment.value());
}
getAssembler().registerSymbol(*Symbol);
Symbol->setExternal(true);
Symbol->setCommon(Size, ByteAlignment);
if (!T.isWindowsMSVCEnvironment() && ByteAlignment > 1) {
SmallString<128> Directive;
raw_svector_ostream OS(Directive);
const MCObjectFileInfo *MFI = getContext().getObjectFileInfo();
OS << " -aligncomm:\"" << Symbol->getName() << "\","
<< Log2_32_Ceil(ByteAlignment.value());
pushSection();
switchSection(MFI->getDrectveSection());
emitBytes(Directive);
popSection();
}
}
void MCWinCOFFStreamer::emitLocalCommonSymbol(MCSymbol *S, uint64_t Size,
Align ByteAlignment) {
auto *Symbol = cast<MCSymbolCOFF>(S);
MCSection *Section = getContext().getObjectFileInfo()->getBSSSection();
pushSection();
switchSection(Section);
emitValueToAlignment(ByteAlignment, 0, 1, 0);
emitLabel(Symbol);
Symbol->setExternal(false);
emitZeros(Size);
popSection();
}
void MCWinCOFFStreamer::emitWeakReference(MCSymbol *AliasS,
const MCSymbol *Symbol) {
auto *Alias = cast<MCSymbolCOFF>(AliasS);
emitSymbolAttribute(Alias, MCSA_Weak);
getAssembler().registerSymbol(*Symbol);
Alias->setVariableValue(MCSymbolRefExpr::create(
Symbol, MCSymbolRefExpr::VK_WEAKREF, getContext()));
}
void MCWinCOFFStreamer::emitZerofill(MCSection *Section, MCSymbol *Symbol,
uint64_t Size, Align ByteAlignment,
SMLoc Loc) {
llvm_unreachable("not implemented");
}
void MCWinCOFFStreamer::emitTBSSSymbol(MCSection *Section, MCSymbol *Symbol,
uint64_t Size, Align ByteAlignment) {
llvm_unreachable("not implemented");
}
// TODO: Implement this if you want to emit .comment section in COFF obj files.
void MCWinCOFFStreamer::emitIdent(StringRef IdentString) {
llvm_unreachable("not implemented");
}
void MCWinCOFFStreamer::emitWinEHHandlerData(SMLoc Loc) {
llvm_unreachable("not implemented");
}
void MCWinCOFFStreamer::emitCGProfileEntry(const MCSymbolRefExpr *From,
const MCSymbolRefExpr *To,
uint64_t Count) {
// Ignore temporary symbols for now.
if (!From->getSymbol().isTemporary() && !To->getSymbol().isTemporary())
getWriter().getCGProfile().push_back({From, To, Count});
}
void MCWinCOFFStreamer::finalizeCGProfileEntry(const MCSymbolRefExpr *&SRE) {
const MCSymbol *S = &SRE->getSymbol();
if (getAssembler().registerSymbol(*S))
cast<MCSymbolCOFF>(S)->setExternal(true);
}
void MCWinCOFFStreamer::finishImpl() {
getContext().getCVContext().finish();
MCAssembler &Asm = getAssembler();
if (Asm.getWriter().getEmitAddrsigSection()) {
// Register the section.
switchSection(Asm.getContext().getCOFFSection(".llvm_addrsig",
COFF::IMAGE_SCN_LNK_REMOVE));
}
if (!Asm.getWriter().getCGProfile().empty()) {
for (auto &E : Asm.getWriter().getCGProfile()) {
finalizeCGProfileEntry(E.From);
finalizeCGProfileEntry(E.To);
}
switchSection(Asm.getContext().getCOFFSection(".llvm.call-graph-profile",
COFF::IMAGE_SCN_LNK_REMOVE));
}
MCObjectStreamer::finishImpl();
}
void MCWinCOFFStreamer::Error(const Twine &Msg) const {
getContext().reportError(SMLoc(), Msg);
}