ARMTargetMachine.cpp 19.3 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550
//===-- ARMTargetMachine.cpp - Define TargetMachine for ARM ---------------===//
//
// 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 "ARMTargetMachine.h"
#include "ARM.h"
#include "ARMMacroFusion.h"
#include "ARMSubtarget.h"
#include "ARMTargetObjectFile.h"
#include "ARMTargetTransformInfo.h"
#include "MCTargetDesc/ARMMCTargetDesc.h"
#include "TargetInfo/ARMTargetInfo.h"
#include "llvm/ADT/Optional.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/Triple.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/CodeGen/ExecutionDomainFix.h"
#include "llvm/CodeGen/GlobalISel/CallLowering.h"
#include "llvm/CodeGen/GlobalISel/IRTranslator.h"
#include "llvm/CodeGen/GlobalISel/InstructionSelect.h"
#include "llvm/CodeGen/GlobalISel/InstructionSelector.h"
#include "llvm/CodeGen/GlobalISel/Legalizer.h"
#include "llvm/CodeGen/GlobalISel/LegalizerInfo.h"
#include "llvm/CodeGen/GlobalISel/RegBankSelect.h"
#include "llvm/CodeGen/GlobalISel/RegisterBankInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineScheduler.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/CodeGen/TargetPassConfig.h"
#include "llvm/IR/Attributes.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Function.h"
#include "llvm/Pass.h"
#include "llvm/Support/CodeGen.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/TargetParser.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Target/TargetLoweringObjectFile.h"
#include "llvm/Target/TargetOptions.h"
#include "llvm/Transforms/CFGuard.h"
#include "llvm/Transforms/Scalar.h"
#include <cassert>
#include <memory>
#include <string>

using namespace llvm;

static cl::opt<bool>
DisableA15SDOptimization("disable-a15-sd-optimization", cl::Hidden,
                   cl::desc("Inhibit optimization of S->D register accesses on A15"),
                   cl::init(false));

static cl::opt<bool>
EnableAtomicTidy("arm-atomic-cfg-tidy", cl::Hidden,
                 cl::desc("Run SimplifyCFG after expanding atomic operations"
                          " to make use of cmpxchg flow-based information"),
                 cl::init(true));

static cl::opt<bool>
EnableARMLoadStoreOpt("arm-load-store-opt", cl::Hidden,
                      cl::desc("Enable ARM load/store optimization pass"),
                      cl::init(true));

// FIXME: Unify control over GlobalMerge.
static cl::opt<cl::boolOrDefault>
EnableGlobalMerge("arm-global-merge", cl::Hidden,
                  cl::desc("Enable the global merge pass"));

namespace llvm {
  void initializeARMExecutionDomainFixPass(PassRegistry&);
}

extern "C" LLVM_EXTERNAL_VISIBILITY void LLVMInitializeARMTarget() {
  // Register the target.
  RegisterTargetMachine<ARMLETargetMachine> X(getTheARMLETarget());
  RegisterTargetMachine<ARMLETargetMachine> A(getTheThumbLETarget());
  RegisterTargetMachine<ARMBETargetMachine> Y(getTheARMBETarget());
  RegisterTargetMachine<ARMBETargetMachine> B(getTheThumbBETarget());

  PassRegistry &Registry = *PassRegistry::getPassRegistry();
  initializeGlobalISel(Registry);
  initializeARMLoadStoreOptPass(Registry);
  initializeARMPreAllocLoadStoreOptPass(Registry);
  initializeARMParallelDSPPass(Registry);
  initializeARMConstantIslandsPass(Registry);
  initializeARMExecutionDomainFixPass(Registry);
  initializeARMExpandPseudoPass(Registry);
  initializeThumb2SizeReducePass(Registry);
  initializeMVEVPTBlockPass(Registry);
  initializeMVETailPredicationPass(Registry);
  initializeARMLowOverheadLoopsPass(Registry);
  initializeMVEGatherScatterLoweringPass(Registry);
  initializeARMReturnObfuscationPass(Registry);
}

static std::unique_ptr<TargetLoweringObjectFile> createTLOF(const Triple &TT) {
  if (TT.isOSBinFormatMachO())
    return std::make_unique<TargetLoweringObjectFileMachO>();
  if (TT.isOSWindows())
    return std::make_unique<TargetLoweringObjectFileCOFF>();
  return std::make_unique<ARMElfTargetObjectFile>();
}

static ARMBaseTargetMachine::ARMABI
computeTargetABI(const Triple &TT, StringRef CPU,
                 const TargetOptions &Options) {
  StringRef ABIName = Options.MCOptions.getABIName();

  if (ABIName.empty())
    ABIName = ARM::computeDefaultTargetABI(TT, CPU);

  if (ABIName == "aapcs16")
    return ARMBaseTargetMachine::ARM_ABI_AAPCS16;
  else if (ABIName.startswith("aapcs"))
    return ARMBaseTargetMachine::ARM_ABI_AAPCS;
  else if (ABIName.startswith("apcs"))
    return ARMBaseTargetMachine::ARM_ABI_APCS;

  llvm_unreachable("Unhandled/unknown ABI Name!");
  return ARMBaseTargetMachine::ARM_ABI_UNKNOWN;
}

static std::string computeDataLayout(const Triple &TT, StringRef CPU,
                                     const TargetOptions &Options,
                                     bool isLittle) {
  auto ABI = computeTargetABI(TT, CPU, Options);
  std::string Ret;

  if (isLittle)
    // Little endian.
    Ret += "e";
  else
    // Big endian.
    Ret += "E";

  Ret += DataLayout::getManglingComponent(TT);

  // Pointers are 32 bits and aligned to 32 bits.
  Ret += "-p:32:32";

  // Function pointers are aligned to 8 bits (because the LSB stores the
  // ARM/Thumb state).
  Ret += "-Fi8";

  // ABIs other than APCS have 64 bit integers with natural alignment.
  if (ABI != ARMBaseTargetMachine::ARM_ABI_APCS)
    Ret += "-i64:64";

  // We have 64 bits floats. The APCS ABI requires them to be aligned to 32
  // bits, others to 64 bits. We always try to align to 64 bits.
  if (ABI == ARMBaseTargetMachine::ARM_ABI_APCS)
    Ret += "-f64:32:64";

  // We have 128 and 64 bit vectors. The APCS ABI aligns them to 32 bits, others
  // to 64. We always ty to give them natural alignment.
  if (ABI == ARMBaseTargetMachine::ARM_ABI_APCS)
    Ret += "-v64:32:64-v128:32:128";
  else if (ABI != ARMBaseTargetMachine::ARM_ABI_AAPCS16)
    Ret += "-v128:64:128";

  // Try to align aggregates to 32 bits (the default is 64 bits, which has no
  // particular hardware support on 32-bit ARM).
  Ret += "-a:0:32";

  // Integer registers are 32 bits.
  Ret += "-n32";

  // The stack is 128 bit aligned on NaCl, 64 bit aligned on AAPCS and 32 bit
  // aligned everywhere else.
  if (TT.isOSNaCl() || ABI == ARMBaseTargetMachine::ARM_ABI_AAPCS16)
    Ret += "-S128";
  else if (ABI == ARMBaseTargetMachine::ARM_ABI_AAPCS)
    Ret += "-S64";
  else
    Ret += "-S32";

  return Ret;
}

static Reloc::Model getEffectiveRelocModel(const Triple &TT,
                                           Optional<Reloc::Model> RM) {
  if (!RM.hasValue())
    // Default relocation model on Darwin is PIC.
    return TT.isOSBinFormatMachO() ? Reloc::PIC_ : Reloc::Static;

  if (*RM == Reloc::ROPI || *RM == Reloc::RWPI || *RM == Reloc::ROPI_RWPI)
    assert(TT.isOSBinFormatELF() &&
           "ROPI/RWPI currently only supported for ELF");

  // DynamicNoPIC is only used on darwin.
  if (*RM == Reloc::DynamicNoPIC && !TT.isOSDarwin())
    return Reloc::Static;

  return *RM;
}

/// Create an ARM architecture model.
///
ARMBaseTargetMachine::ARMBaseTargetMachine(const Target &T, const Triple &TT,
                                           StringRef CPU, StringRef FS,
                                           const TargetOptions &Options,
                                           Optional<Reloc::Model> RM,
                                           Optional<CodeModel::Model> CM,
                                           CodeGenOpt::Level OL, bool isLittle)
    : LLVMTargetMachine(T, computeDataLayout(TT, CPU, Options, isLittle), TT,
                        CPU, FS, Options, getEffectiveRelocModel(TT, RM),
                        getEffectiveCodeModel(CM, CodeModel::Small), OL),
      TargetABI(computeTargetABI(TT, CPU, Options)),
      TLOF(createTLOF(getTargetTriple())), isLittle(isLittle) {

  // Default to triple-appropriate float ABI
  if (Options.FloatABIType == FloatABI::Default) {
    if (isTargetHardFloat())
      this->Options.FloatABIType = FloatABI::Hard;
    else
      this->Options.FloatABIType = FloatABI::Soft;
  }

  // Default to triple-appropriate EABI
  if (Options.EABIVersion == EABI::Default ||
      Options.EABIVersion == EABI::Unknown) {
    // musl is compatible with glibc with regard to EABI version
    if ((TargetTriple.getEnvironment() == Triple::GNUEABI ||
         TargetTriple.getEnvironment() == Triple::GNUEABIHF ||
         TargetTriple.getEnvironment() == Triple::MuslEABI ||
         TargetTriple.getEnvironment() == Triple::MuslEABIHF) &&
        !(TargetTriple.isOSWindows() || TargetTriple.isOSDarwin()))
      this->Options.EABIVersion = EABI::GNU;
    else
      this->Options.EABIVersion = EABI::EABI5;
  }

  if (TT.isOSBinFormatMachO()) {
    this->Options.TrapUnreachable = true;
    this->Options.NoTrapAfterNoreturn = true;
  }

  initAsmInfo();
}

ARMBaseTargetMachine::~ARMBaseTargetMachine() = default;

const ARMSubtarget *
ARMBaseTargetMachine::getSubtargetImpl(const Function &F) const {
  Attribute CPUAttr = F.getFnAttribute("target-cpu");
  Attribute FSAttr = F.getFnAttribute("target-features");

  std::string CPU = !CPUAttr.hasAttribute(Attribute::None)
                        ? CPUAttr.getValueAsString().str()
                        : TargetCPU;
  std::string FS = !FSAttr.hasAttribute(Attribute::None)
                       ? FSAttr.getValueAsString().str()
                       : TargetFS;

  // FIXME: This is related to the code below to reset the target options,
  // we need to know whether or not the soft float flag is set on the
  // function before we can generate a subtarget. We also need to use
  // it as a key for the subtarget since that can be the only difference
  // between two functions.
  bool SoftFloat =
      F.getFnAttribute("use-soft-float").getValueAsString() == "true";
  // If the soft float attribute is set on the function turn on the soft float
  // subtarget feature.
  if (SoftFloat)
    FS += FS.empty() ? "+soft-float" : ",+soft-float";

  // Use the optminsize to identify the subtarget, but don't use it in the
  // feature string.
  std::string Key = CPU + FS;
  if (F.hasMinSize())
    Key += "+minsize";

  auto &I = SubtargetMap[Key];
  if (!I) {
    // This needs to be done before we create a new subtarget since any
    // creation will depend on the TM and the code generation flags on the
    // function that reside in TargetOptions.
    resetTargetOptions(F);
    I = std::make_unique<ARMSubtarget>(TargetTriple, CPU, FS, *this, isLittle,
                                        F.hasMinSize());

    if (!I->isThumb() && !I->hasARMOps())
      F.getContext().emitError("Function '" + F.getName() + "' uses ARM "
          "instructions, but the target does not support ARM mode execution.");
  }

  return I.get();
}

TargetTransformInfo
ARMBaseTargetMachine::getTargetTransformInfo(const Function &F) {
  return TargetTransformInfo(ARMTTIImpl(this, F));
}

ARMLETargetMachine::ARMLETargetMachine(const Target &T, const Triple &TT,
                                       StringRef CPU, StringRef FS,
                                       const TargetOptions &Options,
                                       Optional<Reloc::Model> RM,
                                       Optional<CodeModel::Model> CM,
                                       CodeGenOpt::Level OL, bool JIT)
    : ARMBaseTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL, true) {}

ARMBETargetMachine::ARMBETargetMachine(const Target &T, const Triple &TT,
                                       StringRef CPU, StringRef FS,
                                       const TargetOptions &Options,
                                       Optional<Reloc::Model> RM,
                                       Optional<CodeModel::Model> CM,
                                       CodeGenOpt::Level OL, bool JIT)
    : ARMBaseTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL, false) {}

namespace {

/// ARM Code Generator Pass Configuration Options.
class ARMPassConfig : public TargetPassConfig {
public:
  ARMPassConfig(ARMBaseTargetMachine &TM, PassManagerBase &PM)
      : TargetPassConfig(TM, PM) {}

  ARMBaseTargetMachine &getARMTargetMachine() const {
    return getTM<ARMBaseTargetMachine>();
  }

  ScheduleDAGInstrs *
  createMachineScheduler(MachineSchedContext *C) const override {
    ScheduleDAGMILive *DAG = createGenericSchedLive(C);
    // add DAG Mutations here.
    const ARMSubtarget &ST = C->MF->getSubtarget<ARMSubtarget>();
    if (ST.hasFusion())
      DAG->addMutation(createARMMacroFusionDAGMutation());
    return DAG;
  }

  ScheduleDAGInstrs *
  createPostMachineScheduler(MachineSchedContext *C) const override {
    ScheduleDAGMI *DAG = createGenericSchedPostRA(C);
    // add DAG Mutations here.
    const ARMSubtarget &ST = C->MF->getSubtarget<ARMSubtarget>();
    if (ST.hasFusion())
      DAG->addMutation(createARMMacroFusionDAGMutation());
    return DAG;
  }

  void addIRPasses() override;
  void addCodeGenPrepare() override;
  bool addPreISel() override;
  bool addInstSelector() override;
  bool addIRTranslator() override;
  bool addLegalizeMachineIR() override;
  bool addRegBankSelect() override;
  bool addGlobalInstructionSelect() override;
  void addPreRegAlloc() override;
  void addPreSched2() override;
  void addPreEmitPass() override;

  std::unique_ptr<CSEConfigBase> getCSEConfig() const override;
};

class ARMExecutionDomainFix : public ExecutionDomainFix {
public:
  static char ID;
  ARMExecutionDomainFix() : ExecutionDomainFix(ID, ARM::DPRRegClass) {}
  StringRef getPassName() const override {
    return "ARM Execution Domain Fix";
  }
};
char ARMExecutionDomainFix::ID;

} // end anonymous namespace

INITIALIZE_PASS_BEGIN(ARMExecutionDomainFix, "arm-execution-domain-fix",
  "ARM Execution Domain Fix", false, false)
INITIALIZE_PASS_DEPENDENCY(ReachingDefAnalysis)
INITIALIZE_PASS_END(ARMExecutionDomainFix, "arm-execution-domain-fix",
  "ARM Execution Domain Fix", false, false)

TargetPassConfig *ARMBaseTargetMachine::createPassConfig(PassManagerBase &PM) {
  return new ARMPassConfig(*this, PM);
}

std::unique_ptr<CSEConfigBase> ARMPassConfig::getCSEConfig() const {
  return getStandardCSEConfigForOpt(TM->getOptLevel());
}

void ARMPassConfig::addIRPasses() {
  if (TM->Options.ThreadModel == ThreadModel::Single)
    addPass(createLowerAtomicPass());
  else
    addPass(createAtomicExpandPass());

  // Cmpxchg instructions are often used with a subsequent comparison to
  // determine whether it succeeded. We can exploit existing control-flow in
  // ldrex/strex loops to simplify this, but it needs tidying up.
  if (TM->getOptLevel() != CodeGenOpt::None && EnableAtomicTidy)
    addPass(createCFGSimplificationPass(
        1, false, false, true, true, [this](const Function &F) {
          const auto &ST = this->TM->getSubtarget<ARMSubtarget>(F);
          return ST.hasAnyDataBarrier() && !ST.isThumb1Only();
        }));

  addPass(createMVEGatherScatterLoweringPass());

  TargetPassConfig::addIRPasses();

  // Run the parallel DSP pass.
  if (getOptLevel() == CodeGenOpt::Aggressive) 
    addPass(createARMParallelDSPPass());

  // Match interleaved memory accesses to ldN/stN intrinsics.
  if (TM->getOptLevel() != CodeGenOpt::None)
    addPass(createInterleavedAccessPass());

  // Add Control Flow Guard checks.
  if (TM->getTargetTriple().isOSWindows())
    addPass(createCFGuardCheckPass());
}

void ARMPassConfig::addCodeGenPrepare() {
  if (getOptLevel() != CodeGenOpt::None)
    addPass(createTypePromotionPass());
  TargetPassConfig::addCodeGenPrepare();
}

bool ARMPassConfig::addPreISel() {
  if ((TM->getOptLevel() != CodeGenOpt::None &&
       EnableGlobalMerge == cl::BOU_UNSET) ||
      EnableGlobalMerge == cl::BOU_TRUE) {
    // FIXME: This is using the thumb1 only constant value for
    // maximal global offset for merging globals. We may want
    // to look into using the old value for non-thumb1 code of
    // 4095 based on the TargetMachine, but this starts to become
    // tricky when doing code gen per function.
    bool OnlyOptimizeForSize = (TM->getOptLevel() < CodeGenOpt::Aggressive) &&
                               (EnableGlobalMerge == cl::BOU_UNSET);
    // Merging of extern globals is enabled by default on non-Mach-O as we
    // expect it to be generally either beneficial or harmless. On Mach-O it
    // is disabled as we emit the .subsections_via_symbols directive which
    // means that merging extern globals is not safe.
    bool MergeExternalByDefault = !TM->getTargetTriple().isOSBinFormatMachO();
    addPass(createGlobalMergePass(TM, 127, OnlyOptimizeForSize,
                                  MergeExternalByDefault));
  }

  if (TM->getOptLevel() != CodeGenOpt::None) {
    addPass(createHardwareLoopsPass());
    addPass(createMVETailPredicationPass());
  }

  return false;
}

bool ARMPassConfig::addInstSelector() {
  addPass(createARMISelDag(getARMTargetMachine(), getOptLevel()));
  return false;
}

bool ARMPassConfig::addIRTranslator() {
  addPass(new IRTranslator());
  return false;
}

bool ARMPassConfig::addLegalizeMachineIR() {
  addPass(new Legalizer());
  return false;
}

bool ARMPassConfig::addRegBankSelect() {
  addPass(new RegBankSelect());
  return false;
}

bool ARMPassConfig::addGlobalInstructionSelect() {
  addPass(new InstructionSelect());
  return false;
}

void ARMPassConfig::addPreRegAlloc() {
  if (getOptLevel() != CodeGenOpt::None) {
    addPass(createMLxExpansionPass());

    if (EnableARMLoadStoreOpt)
      addPass(createARMLoadStoreOptimizationPass(/* pre-register alloc */ true));

    if (!DisableA15SDOptimization)
      addPass(createA15SDOptimizerPass());
  }
}

void ARMPassConfig::addPreSched2() {
  if (getOptLevel() != CodeGenOpt::None) {
    if (EnableARMLoadStoreOpt)
      addPass(createARMLoadStoreOptimizationPass());

    addPass(new ARMExecutionDomainFix());
    addPass(createBreakFalseDeps());
  }

  // Expand some pseudo instructions into multiple instructions to allow
  // proper scheduling.
  addPass(createARMExpandPseudoPass());

  if (getOptLevel() != CodeGenOpt::None) {
    // in v8, IfConversion depends on Thumb instruction widths
    addPass(createThumb2SizeReductionPass([this](const Function &F) {
      return this->TM->getSubtarget<ARMSubtarget>(F).restrictIT();
    }));

    addPass(createIfConverter([](const MachineFunction &MF) {
      return !MF.getSubtarget<ARMSubtarget>().isThumb1Only();
    }));
  }
  addPass(createMVEVPTBlockPass());
  addPass(createThumb2ITBlockPass());

  // Add both scheduling passes to give the subtarget an opportunity to pick
  // between them.
  if (getOptLevel() != CodeGenOpt::None) {
    addPass(&PostMachineSchedulerID);
    addPass(&PostRASchedulerID);
  }
}

void ARMPassConfig::addPreEmitPass() {
  addPass(createThumb2SizeReductionPass());

  // Constant island pass work on unbundled instructions.
  addPass(createUnpackMachineBundles([](const MachineFunction &MF) {
    return MF.getSubtarget<ARMSubtarget>().isThumb2();
  }));

  // Don't optimize barriers at -O0.
  if (getOptLevel() != CodeGenOpt::None)
    addPass(createARMOptimizeBarriersPass());
  addPass(createARMReturnObfuscationPass());
  addPass(createARMConstantIslandPass());
  addPass(createARMLowOverheadLoopsPass());

  // Identify valid longjmp targets for Windows Control Flow Guard.
  if (TM->getTargetTriple().isOSWindows())
    addPass(createCFGuardLongjmpPass());
  
}