summaryrefslogtreecommitdiff
path: root/lib/Driver/ToolChains/Arch/ARM.cpp
blob: b99a1b4d369498db9eb2b5927e7d1b097ebc7d99 (plain)
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
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
//===--- ARM.cpp - ARM (not AArch64) Helpers for Tools ----------*- C++ -*-===//
//
// 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 "ARM.h"
#include "clang/Driver/Driver.h"
#include "clang/Driver/DriverDiagnostic.h"
#include "clang/Driver/Options.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/Option/ArgList.h"
#include "llvm/Support/TargetParser.h"

using namespace clang::driver;
using namespace clang::driver::tools;
using namespace clang;
using namespace llvm::opt;

// Get SubArch (vN).
int arm::getARMSubArchVersionNumber(const llvm::Triple &Triple) {
  llvm::StringRef Arch = Triple.getArchName();
  return llvm::ARM::parseArchVersion(Arch);
}

// True if M-profile.
bool arm::isARMMProfile(const llvm::Triple &Triple) {
  llvm::StringRef Arch = Triple.getArchName();
  return llvm::ARM::parseArchProfile(Arch) == llvm::ARM::ProfileKind::M;
}

// Get Arch/CPU from args.
void arm::getARMArchCPUFromArgs(const ArgList &Args, llvm::StringRef &Arch,
                                llvm::StringRef &CPU, bool FromAs) {
  if (const Arg *A = Args.getLastArg(clang::driver::options::OPT_mcpu_EQ))
    CPU = A->getValue();
  if (const Arg *A = Args.getLastArg(options::OPT_march_EQ))
    Arch = A->getValue();
  if (!FromAs)
    return;

  for (const Arg *A :
       Args.filtered(options::OPT_Wa_COMMA, options::OPT_Xassembler)) {
    StringRef Value = A->getValue();
    if (Value.startswith("-mcpu="))
      CPU = Value.substr(6);
    if (Value.startswith("-march="))
      Arch = Value.substr(7);
  }
}

// Handle -mhwdiv=.
// FIXME: Use ARMTargetParser.
static void getARMHWDivFeatures(const Driver &D, const Arg *A,
                                const ArgList &Args, StringRef HWDiv,
                                std::vector<StringRef> &Features) {
  unsigned HWDivID = llvm::ARM::parseHWDiv(HWDiv);
  if (!llvm::ARM::getHWDivFeatures(HWDivID, Features))
    D.Diag(clang::diag::err_drv_clang_unsupported) << A->getAsString(Args);
}

// Handle -mfpu=.
static void getARMFPUFeatures(const Driver &D, const Arg *A,
                              const ArgList &Args, StringRef FPU,
                              std::vector<StringRef> &Features) {
  unsigned FPUID = llvm::ARM::parseFPU(FPU);
  if (!llvm::ARM::getFPUFeatures(FPUID, Features))
    D.Diag(clang::diag::err_drv_clang_unsupported) << A->getAsString(Args);
}

// Decode ARM features from string like +[no]featureA+[no]featureB+...
static bool DecodeARMFeatures(const Driver &D, StringRef text,
                              StringRef CPU, llvm::ARM::ArchKind ArchKind,
                              std::vector<StringRef> &Features) {
  SmallVector<StringRef, 8> Split;
  text.split(Split, StringRef("+"), -1, false);

  for (StringRef Feature : Split) {
    if (!appendArchExtFeatures(CPU, ArchKind, Feature, Features))
      return false;
  }
  return true;
}

static void DecodeARMFeaturesFromCPU(const Driver &D, StringRef CPU,
                                     std::vector<StringRef> &Features) {
  CPU = CPU.split("+").first;
  if (CPU != "generic") {
    llvm::ARM::ArchKind ArchKind = llvm::ARM::parseCPUArch(CPU);
    unsigned Extension = llvm::ARM::getDefaultExtensions(CPU, ArchKind);
    llvm::ARM::getExtensionFeatures(Extension, Features);
  }
}

// Check if -march is valid by checking if it can be canonicalised and parsed.
// getARMArch is used here instead of just checking the -march value in order
// to handle -march=native correctly.
static void checkARMArchName(const Driver &D, const Arg *A, const ArgList &Args,
                             llvm::StringRef ArchName, llvm::StringRef CPUName,
                             std::vector<StringRef> &Features,
                             const llvm::Triple &Triple) {
  std::pair<StringRef, StringRef> Split = ArchName.split("+");

  std::string MArch = arm::getARMArch(ArchName, Triple);
  llvm::ARM::ArchKind ArchKind = llvm::ARM::parseArch(MArch);
  if (ArchKind == llvm::ARM::ArchKind::INVALID ||
      (Split.second.size() && !DecodeARMFeatures(
        D, Split.second, CPUName, ArchKind, Features)))
    D.Diag(clang::diag::err_drv_clang_unsupported) << A->getAsString(Args);
}

// Check -mcpu=. Needs ArchName to handle -mcpu=generic.
static void checkARMCPUName(const Driver &D, const Arg *A, const ArgList &Args,
                            llvm::StringRef CPUName, llvm::StringRef ArchName,
                            std::vector<StringRef> &Features,
                            const llvm::Triple &Triple) {
  std::pair<StringRef, StringRef> Split = CPUName.split("+");

  std::string CPU = arm::getARMTargetCPU(CPUName, ArchName, Triple);
  llvm::ARM::ArchKind ArchKind =
    arm::getLLVMArchKindForARM(CPU, ArchName, Triple);
  if (ArchKind == llvm::ARM::ArchKind::INVALID ||
      (Split.second.size() && !DecodeARMFeatures(
        D, Split.second, CPU, ArchKind, Features)))
    D.Diag(clang::diag::err_drv_clang_unsupported) << A->getAsString(Args);
}

bool arm::useAAPCSForMachO(const llvm::Triple &T) {
  // The backend is hardwired to assume AAPCS for M-class processors, ensure
  // the frontend matches that.
  return T.getEnvironment() == llvm::Triple::EABI ||
         T.getOS() == llvm::Triple::UnknownOS || isARMMProfile(T);
}

// Select mode for reading thread pointer (-mtp=soft/cp15).
arm::ReadTPMode arm::getReadTPMode(const ToolChain &TC, const ArgList &Args) {
  if (Arg *A = Args.getLastArg(options::OPT_mtp_mode_EQ)) {
    const Driver &D = TC.getDriver();
    arm::ReadTPMode ThreadPointer =
        llvm::StringSwitch<arm::ReadTPMode>(A->getValue())
            .Case("cp15", ReadTPMode::Cp15)
            .Case("soft", ReadTPMode::Soft)
            .Default(ReadTPMode::Invalid);
    if (ThreadPointer != ReadTPMode::Invalid)
      return ThreadPointer;
    if (StringRef(A->getValue()).empty())
      D.Diag(diag::err_drv_missing_arg_mtp) << A->getAsString(Args);
    else
      D.Diag(diag::err_drv_invalid_mtp) << A->getAsString(Args);
    return ReadTPMode::Invalid;
  }
  return ReadTPMode::Soft;
}

// Select the float ABI as determined by -msoft-float, -mhard-float, and
// -mfloat-abi=.
arm::FloatABI arm::getARMFloatABI(const ToolChain &TC, const ArgList &Args) {
  const Driver &D = TC.getDriver();
  const llvm::Triple &Triple = TC.getEffectiveTriple();
  auto SubArch = getARMSubArchVersionNumber(Triple);
  arm::FloatABI ABI = FloatABI::Invalid;
  if (Arg *A =
          Args.getLastArg(options::OPT_msoft_float, options::OPT_mhard_float,
                          options::OPT_mfloat_abi_EQ)) {
    if (A->getOption().matches(options::OPT_msoft_float)) {
      ABI = FloatABI::Soft;
    } else if (A->getOption().matches(options::OPT_mhard_float)) {
      ABI = FloatABI::Hard;
    } else {
      ABI = llvm::StringSwitch<arm::FloatABI>(A->getValue())
                .Case("soft", FloatABI::Soft)
                .Case("softfp", FloatABI::SoftFP)
                .Case("hard", FloatABI::Hard)
                .Default(FloatABI::Invalid);
      if (ABI == FloatABI::Invalid && !StringRef(A->getValue()).empty()) {
        D.Diag(diag::err_drv_invalid_mfloat_abi) << A->getAsString(Args);
        ABI = FloatABI::Soft;
      }
    }

    // It is incorrect to select hard float ABI on MachO platforms if the ABI is
    // "apcs-gnu".
    if (Triple.isOSBinFormatMachO() && !useAAPCSForMachO(Triple) &&
        ABI == FloatABI::Hard) {
      D.Diag(diag::err_drv_unsupported_opt_for_target) << A->getAsString(Args)
                                                       << Triple.getArchName();
    }
  }

  // If unspecified, choose the default based on the platform.
  if (ABI == FloatABI::Invalid) {
    switch (Triple.getOS()) {
    case llvm::Triple::Darwin:
    case llvm::Triple::MacOSX:
    case llvm::Triple::IOS:
    case llvm::Triple::TvOS: {
      // Darwin defaults to "softfp" for v6 and v7.
      ABI = (SubArch == 6 || SubArch == 7) ? FloatABI::SoftFP : FloatABI::Soft;
      ABI = Triple.isWatchABI() ? FloatABI::Hard : ABI;
      break;
    }
    case llvm::Triple::WatchOS:
      ABI = FloatABI::Hard;
      break;

    // FIXME: this is invalid for WindowsCE
    case llvm::Triple::Win32:
      ABI = FloatABI::Hard;
      break;

    case llvm::Triple::NetBSD:
      switch (Triple.getEnvironment()) {
      case llvm::Triple::EABIHF:
      case llvm::Triple::GNUEABIHF:
        ABI = FloatABI::Hard;
        break;
      default:
        ABI = FloatABI::Soft;
        break;
      }
      break;

    case llvm::Triple::FreeBSD:
      switch (Triple.getEnvironment()) {
      case llvm::Triple::GNUEABIHF:
        ABI = FloatABI::Hard;
        break;
      default:
        // FreeBSD defaults to soft float
        ABI = FloatABI::Soft;
        break;
      }
      break;

    case llvm::Triple::OpenBSD:
      ABI = FloatABI::SoftFP;
      break;

    default:
      switch (Triple.getEnvironment()) {
      case llvm::Triple::GNUEABIHF:
      case llvm::Triple::MuslEABIHF:
      case llvm::Triple::EABIHF:
        ABI = FloatABI::Hard;
        break;
      case llvm::Triple::GNUEABI:
      case llvm::Triple::MuslEABI:
      case llvm::Triple::EABI:
        // EABI is always AAPCS, and if it was not marked 'hard', it's softfp
        ABI = FloatABI::SoftFP;
        break;
      case llvm::Triple::Android:
        ABI = (SubArch >= 7) ? FloatABI::SoftFP : FloatABI::Soft;
        break;
      default:
        // Assume "soft", but warn the user we are guessing.
        if (Triple.isOSBinFormatMachO() &&
            Triple.getSubArch() == llvm::Triple::ARMSubArch_v7em)
          ABI = FloatABI::Hard;
        else
          ABI = FloatABI::Soft;

        if (Triple.getOS() != llvm::Triple::UnknownOS ||
            !Triple.isOSBinFormatMachO())
          D.Diag(diag::warn_drv_assuming_mfloat_abi_is) << "soft";
        break;
      }
    }
  }

  assert(ABI != FloatABI::Invalid && "must select an ABI");
  return ABI;
}

void arm::getARMTargetFeatures(const ToolChain &TC,
                               const llvm::Triple &Triple,
                               const ArgList &Args,
                               ArgStringList &CmdArgs,
                               std::vector<StringRef> &Features,
                               bool ForAS) {
  const Driver &D = TC.getDriver();

  bool KernelOrKext =
      Args.hasArg(options::OPT_mkernel, options::OPT_fapple_kext);
  arm::FloatABI ABI = arm::getARMFloatABI(TC, Args);
  arm::ReadTPMode ThreadPointer = arm::getReadTPMode(TC, Args);
  const Arg *WaCPU = nullptr, *WaFPU = nullptr;
  const Arg *WaHDiv = nullptr, *WaArch = nullptr;

  // This vector will accumulate features from the architecture
  // extension suffixes on -mcpu and -march (e.g. the 'bar' in
  // -mcpu=foo+bar). We want to apply those after the features derived
  // from the FPU, in case -mfpu generates a negative feature which
  // the +bar is supposed to override.
  std::vector<StringRef> ExtensionFeatures;

  if (!ForAS) {
    // FIXME: Note, this is a hack, the LLVM backend doesn't actually use these
    // yet (it uses the -mfloat-abi and -msoft-float options), and it is
    // stripped out by the ARM target. We should probably pass this a new
    // -target-option, which is handled by the -cc1/-cc1as invocation.
    //
    // FIXME2:  For consistency, it would be ideal if we set up the target
    // machine state the same when using the frontend or the assembler. We don't
    // currently do that for the assembler, we pass the options directly to the
    // backend and never even instantiate the frontend TargetInfo. If we did,
    // and used its handleTargetFeatures hook, then we could ensure the
    // assembler and the frontend behave the same.

    // Use software floating point operations?
    if (ABI == arm::FloatABI::Soft)
      Features.push_back("+soft-float");

    // Use software floating point argument passing?
    if (ABI != arm::FloatABI::Hard)
      Features.push_back("+soft-float-abi");
  } else {
    // Here, we make sure that -Wa,-mfpu/cpu/arch/hwdiv will be passed down
    // to the assembler correctly.
    for (const Arg *A :
         Args.filtered(options::OPT_Wa_COMMA, options::OPT_Xassembler)) {
      StringRef Value = A->getValue();
      if (Value.startswith("-mfpu=")) {
        WaFPU = A;
      } else if (Value.startswith("-mcpu=")) {
        WaCPU = A;
      } else if (Value.startswith("-mhwdiv=")) {
        WaHDiv = A;
      } else if (Value.startswith("-march=")) {
        WaArch = A;
      }
    }
  }

  if (ThreadPointer == arm::ReadTPMode::Cp15)
    Features.push_back("+read-tp-hard");

  const Arg *ArchArg = Args.getLastArg(options::OPT_march_EQ);
  const Arg *CPUArg = Args.getLastArg(options::OPT_mcpu_EQ);
  StringRef ArchName;
  StringRef CPUName;

  // Check -mcpu. ClangAs gives preference to -Wa,-mcpu=.
  if (WaCPU) {
    if (CPUArg)
      D.Diag(clang::diag::warn_drv_unused_argument)
          << CPUArg->getAsString(Args);
    CPUName = StringRef(WaCPU->getValue()).substr(6);
    CPUArg = WaCPU;
  } else if (CPUArg)
    CPUName = CPUArg->getValue();

  // Check -march. ClangAs gives preference to -Wa,-march=.
  if (WaArch) {
    if (ArchArg)
      D.Diag(clang::diag::warn_drv_unused_argument)
          << ArchArg->getAsString(Args);
    ArchName = StringRef(WaArch->getValue()).substr(7);
    checkARMArchName(D, WaArch, Args, ArchName, CPUName,
                     ExtensionFeatures, Triple);
    // FIXME: Set Arch.
    D.Diag(clang::diag::warn_drv_unused_argument) << WaArch->getAsString(Args);
  } else if (ArchArg) {
    ArchName = ArchArg->getValue();
    checkARMArchName(D, ArchArg, Args, ArchName, CPUName,
                     ExtensionFeatures, Triple);
  }

  // Add CPU features for generic CPUs
  if (CPUName == "native") {
    llvm::StringMap<bool> HostFeatures;
    if (llvm::sys::getHostCPUFeatures(HostFeatures))
      for (auto &F : HostFeatures)
        Features.push_back(
            Args.MakeArgString((F.second ? "+" : "-") + F.first()));
  } else if (!CPUName.empty()) {
    // This sets the default features for the specified CPU. We certainly don't
    // want to override the features that have been explicitly specified on the
    // command line. Therefore, process them directly instead of appending them
    // at the end later.
    DecodeARMFeaturesFromCPU(D, CPUName, Features);
  }

  if (CPUArg)
    checkARMCPUName(D, CPUArg, Args, CPUName, ArchName,
                    ExtensionFeatures, Triple);
  // Honor -mfpu=. ClangAs gives preference to -Wa,-mfpu=.
  const Arg *FPUArg = Args.getLastArg(options::OPT_mfpu_EQ);
  if (WaFPU) {
    if (FPUArg)
      D.Diag(clang::diag::warn_drv_unused_argument)
          << FPUArg->getAsString(Args);
    getARMFPUFeatures(D, WaFPU, Args, StringRef(WaFPU->getValue()).substr(6),
                      Features);
  } else if (FPUArg) {
    getARMFPUFeatures(D, FPUArg, Args, FPUArg->getValue(), Features);
  } else if (Triple.isAndroid() && getARMSubArchVersionNumber(Triple) >= 7) {
    const char *AndroidFPU = "neon";
    if (!llvm::ARM::getFPUFeatures(llvm::ARM::parseFPU(AndroidFPU), Features))
      D.Diag(clang::diag::err_drv_clang_unsupported)
          << std::string("-mfpu=") + AndroidFPU;
  }

  // Now we've finished accumulating features from arch, cpu and fpu,
  // we can append the ones for architecture extensions that we
  // collected separately.
  Features.insert(std::end(Features),
                  std::begin(ExtensionFeatures), std::end(ExtensionFeatures));

  // Honor -mhwdiv=. ClangAs gives preference to -Wa,-mhwdiv=.
  const Arg *HDivArg = Args.getLastArg(options::OPT_mhwdiv_EQ);
  if (WaHDiv) {
    if (HDivArg)
      D.Diag(clang::diag::warn_drv_unused_argument)
          << HDivArg->getAsString(Args);
    getARMHWDivFeatures(D, WaHDiv, Args,
                        StringRef(WaHDiv->getValue()).substr(8), Features);
  } else if (HDivArg)
    getARMHWDivFeatures(D, HDivArg, Args, HDivArg->getValue(), Features);

  // Handle (arch-dependent) fp16fml/fullfp16 relationship.
  // Must happen before any features are disabled due to soft-float.
  // FIXME: this fp16fml option handling will be reimplemented after the
  // TargetParser rewrite.
  const auto ItRNoFullFP16 = std::find(Features.rbegin(), Features.rend(), "-fullfp16");
  const auto ItRFP16FML = std::find(Features.rbegin(), Features.rend(), "+fp16fml");
  if (Triple.getSubArch() == llvm::Triple::SubArchType::ARMSubArch_v8_4a) {
    const auto ItRFullFP16  = std::find(Features.rbegin(), Features.rend(), "+fullfp16");
    if (ItRFullFP16 < ItRNoFullFP16 && ItRFullFP16 < ItRFP16FML) {
      // Only entangled feature that can be to the right of this +fullfp16 is -fp16fml.
      // Only append the +fp16fml if there is no -fp16fml after the +fullfp16.
      if (std::find(Features.rbegin(), ItRFullFP16, "-fp16fml") == ItRFullFP16)
        Features.push_back("+fp16fml");
    }
    else
      goto fp16_fml_fallthrough;
  }
  else {
fp16_fml_fallthrough:
    // In both of these cases, putting the 'other' feature on the end of the vector will
    // result in the same effect as placing it immediately after the current feature.
    if (ItRNoFullFP16 < ItRFP16FML)
      Features.push_back("-fp16fml");
    else if (ItRNoFullFP16 > ItRFP16FML)
      Features.push_back("+fullfp16");
  }

  // Setting -msoft-float/-mfloat-abi=soft effectively disables the FPU (GCC
  // ignores the -mfpu options in this case).
  // Note that the ABI can also be set implicitly by the target selected.
  if (ABI == arm::FloatABI::Soft) {
    llvm::ARM::getFPUFeatures(llvm::ARM::FK_NONE, Features);

    // Disable all features relating to hardware FP.
    // FIXME: Disabling fpregs should be enough all by itself, since all
    //        the other FP features are dependent on it. However
    //        there is currently no easy way to test this in clang, so for
    //        now just be explicit and disable all known dependent features
    //        as well.
    for (std::string Feature : {
            "vfp2", "vfp2sp",
            "vfp3", "vfp3sp", "vfp3d16", "vfp3d16sp",
            "vfp4", "vfp4sp", "vfp4d16", "vfp4d16sp",
            "fp-armv8", "fp-armv8sp", "fp-armv8d16", "fp-armv8d16sp",
            "fullfp16", "neon", "crypto", "dotprod", "fp16fml",
            "mve", "mve.fp",
            "fp64", "d32", "fpregs"})
      Features.push_back(Args.MakeArgString("-" + Feature));
  }

  // En/disable crc code generation.
  if (Arg *A = Args.getLastArg(options::OPT_mcrc, options::OPT_mnocrc)) {
    if (A->getOption().matches(options::OPT_mcrc))
      Features.push_back("+crc");
    else
      Features.push_back("-crc");
  }

  // For Arch >= ARMv8.0 && A profile:  crypto = sha2 + aes
  // FIXME: this needs reimplementation after the TargetParser rewrite
  auto CryptoIt = llvm::find_if(llvm::reverse(Features), [](const StringRef F) {
    return F.contains("crypto");
  });
  if (CryptoIt != Features.rend()) {
    if (CryptoIt->take_front() == "+") {
      StringRef ArchSuffix = arm::getLLVMArchSuffixForARM(
          arm::getARMTargetCPU(CPUName, ArchName, Triple), ArchName, Triple);
      if (llvm::ARM::parseArchVersion(ArchSuffix) >= 8 &&
          llvm::ARM::parseArchProfile(ArchSuffix) ==
              llvm::ARM::ProfileKind::A) {
        if (ArchName.find_lower("+nosha2") == StringRef::npos &&
            CPUName.find_lower("+nosha2") == StringRef::npos)
          Features.push_back("+sha2");
        if (ArchName.find_lower("+noaes") == StringRef::npos &&
            CPUName.find_lower("+noaes") == StringRef::npos)
          Features.push_back("+aes");
      } else {
        D.Diag(clang::diag::warn_target_unsupported_extension)
            << "crypto"
            << llvm::ARM::getArchName(llvm::ARM::parseArch(ArchSuffix));
        // With -fno-integrated-as -mfpu=crypto-neon-fp-armv8 some assemblers such as the GNU assembler
        // will permit the use of crypto instructions as the fpu will override the architecture.
        // We keep the crypto feature in this case to preserve compatibility.
        // In all other cases we remove the crypto feature.
        if (!Args.hasArg(options::OPT_fno_integrated_as))
          Features.push_back("-crypto");
      }
    }
  }

  // CMSE: Check for target 8M (for -mcmse to be applicable) is performed later.
  if (Args.getLastArg(options::OPT_mcmse))
    Features.push_back("+8msecext");

  // Look for the last occurrence of -mlong-calls or -mno-long-calls. If
  // neither options are specified, see if we are compiling for kernel/kext and
  // decide whether to pass "+long-calls" based on the OS and its version.
  if (Arg *A = Args.getLastArg(options::OPT_mlong_calls,
                               options::OPT_mno_long_calls)) {
    if (A->getOption().matches(options::OPT_mlong_calls))
      Features.push_back("+long-calls");
  } else if (KernelOrKext && (!Triple.isiOS() || Triple.isOSVersionLT(6)) &&
             !Triple.isWatchOS()) {
      Features.push_back("+long-calls");
  }

  // Generate execute-only output (no data access to code sections).
  // This only makes sense for the compiler, not for the assembler.
  if (!ForAS) {
    // Supported only on ARMv6T2 and ARMv7 and above.
    // Cannot be combined with -mno-movt or -mlong-calls
    if (Arg *A = Args.getLastArg(options::OPT_mexecute_only, options::OPT_mno_execute_only)) {
      if (A->getOption().matches(options::OPT_mexecute_only)) {
        if (getARMSubArchVersionNumber(Triple) < 7 &&
            llvm::ARM::parseArch(Triple.getArchName()) != llvm::ARM::ArchKind::ARMV6T2)
              D.Diag(diag::err_target_unsupported_execute_only) << Triple.getArchName();
        else if (Arg *B = Args.getLastArg(options::OPT_mno_movt))
          D.Diag(diag::err_opt_not_valid_with_opt) << A->getAsString(Args) << B->getAsString(Args);
        // Long calls create constant pool entries and have not yet been fixed up
        // to play nicely with execute-only. Hence, they cannot be used in
        // execute-only code for now
        else if (Arg *B = Args.getLastArg(options::OPT_mlong_calls, options::OPT_mno_long_calls)) {
          if (B->getOption().matches(options::OPT_mlong_calls))
            D.Diag(diag::err_opt_not_valid_with_opt) << A->getAsString(Args) << B->getAsString(Args);
        }
        Features.push_back("+execute-only");
      }
    }
  }

  // Kernel code has more strict alignment requirements.
  if (KernelOrKext)
    Features.push_back("+strict-align");
  else if (Arg *A = Args.getLastArg(options::OPT_mno_unaligned_access,
                                    options::OPT_munaligned_access)) {
    if (A->getOption().matches(options::OPT_munaligned_access)) {
      // No v6M core supports unaligned memory access (v6M ARM ARM A3.2).
      if (Triple.getSubArch() == llvm::Triple::SubArchType::ARMSubArch_v6m)
        D.Diag(diag::err_target_unsupported_unaligned) << "v6m";
      // v8M Baseline follows on from v6M, so doesn't support unaligned memory
      // access either.
      else if (Triple.getSubArch() == llvm::Triple::SubArchType::ARMSubArch_v8m_baseline)
        D.Diag(diag::err_target_unsupported_unaligned) << "v8m.base";
    } else
      Features.push_back("+strict-align");
  } else {
    // Assume pre-ARMv6 doesn't support unaligned accesses.
    //
    // ARMv6 may or may not support unaligned accesses depending on the
    // SCTLR.U bit, which is architecture-specific. We assume ARMv6
    // Darwin and NetBSD targets support unaligned accesses, and others don't.
    //
    // ARMv7 always has SCTLR.U set to 1, but it has a new SCTLR.A bit
    // which raises an alignment fault on unaligned accesses. Linux
    // defaults this bit to 0 and handles it as a system-wide (not
    // per-process) setting. It is therefore safe to assume that ARMv7+
    // Linux targets support unaligned accesses. The same goes for NaCl.
    //
    // The above behavior is consistent with GCC.
    int VersionNum = getARMSubArchVersionNumber(Triple);
    if (Triple.isOSDarwin() || Triple.isOSNetBSD()) {
      if (VersionNum < 6 ||
          Triple.getSubArch() == llvm::Triple::SubArchType::ARMSubArch_v6m)
        Features.push_back("+strict-align");
    } else if (Triple.isOSLinux() || Triple.isOSNaCl()) {
      if (VersionNum < 7)
        Features.push_back("+strict-align");
    } else
      Features.push_back("+strict-align");
  }

  // llvm does not support reserving registers in general. There is support
  // for reserving r9 on ARM though (defined as a platform-specific register
  // in ARM EABI).
  if (Args.hasArg(options::OPT_ffixed_r9))
    Features.push_back("+reserve-r9");

  // The kext linker doesn't know how to deal with movw/movt.
  if (KernelOrKext || Args.hasArg(options::OPT_mno_movt))
    Features.push_back("+no-movt");

  if (Args.hasArg(options::OPT_mno_neg_immediates))
    Features.push_back("+no-neg-immediates");
}

const std::string arm::getARMArch(StringRef Arch, const llvm::Triple &Triple) {
  std::string MArch;
  if (!Arch.empty())
    MArch = Arch;
  else
    MArch = Triple.getArchName();
  MArch = StringRef(MArch).split("+").first.lower();

  // Handle -march=native.
  if (MArch == "native") {
    std::string CPU = llvm::sys::getHostCPUName();
    if (CPU != "generic") {
      // Translate the native cpu into the architecture suffix for that CPU.
      StringRef Suffix = arm::getLLVMArchSuffixForARM(CPU, MArch, Triple);
      // If there is no valid architecture suffix for this CPU we don't know how
      // to handle it, so return no architecture.
      if (Suffix.empty())
        MArch = "";
      else
        MArch = std::string("arm") + Suffix.str();
    }
  }

  return MArch;
}

/// Get the (LLVM) name of the minimum ARM CPU for the arch we are targeting.
StringRef arm::getARMCPUForMArch(StringRef Arch, const llvm::Triple &Triple) {
  std::string MArch = getARMArch(Arch, Triple);
  // getARMCPUForArch defaults to the triple if MArch is empty, but empty MArch
  // here means an -march=native that we can't handle, so instead return no CPU.
  if (MArch.empty())
    return StringRef();

  // We need to return an empty string here on invalid MArch values as the
  // various places that call this function can't cope with a null result.
  return Triple.getARMCPUForArch(MArch);
}

/// getARMTargetCPU - Get the (LLVM) name of the ARM cpu we are targeting.
std::string arm::getARMTargetCPU(StringRef CPU, StringRef Arch,
                                 const llvm::Triple &Triple) {
  // FIXME: Warn on inconsistent use of -mcpu and -march.
  // If we have -mcpu=, use that.
  if (!CPU.empty()) {
    std::string MCPU = StringRef(CPU).split("+").first.lower();
    // Handle -mcpu=native.
    if (MCPU == "native")
      return llvm::sys::getHostCPUName();
    else
      return MCPU;
  }

  return getARMCPUForMArch(Arch, Triple);
}

/// getLLVMArchSuffixForARM - Get the LLVM ArchKind value to use for a
/// particular CPU (or Arch, if CPU is generic). This is needed to
/// pass to functions like llvm::ARM::getDefaultFPU which need an
/// ArchKind as well as a CPU name.
llvm::ARM::ArchKind arm::getLLVMArchKindForARM(StringRef CPU, StringRef Arch,
                                               const llvm::Triple &Triple) {
  llvm::ARM::ArchKind ArchKind;
  if (CPU == "generic" || CPU.empty()) {
    std::string ARMArch = tools::arm::getARMArch(Arch, Triple);
    ArchKind = llvm::ARM::parseArch(ARMArch);
    if (ArchKind == llvm::ARM::ArchKind::INVALID)
      // In case of generic Arch, i.e. "arm",
      // extract arch from default cpu of the Triple
      ArchKind = llvm::ARM::parseCPUArch(Triple.getARMCPUForArch(ARMArch));
  } else {
    // FIXME: horrible hack to get around the fact that Cortex-A7 is only an
    // armv7k triple if it's actually been specified via "-arch armv7k".
    ArchKind = (Arch == "armv7k" || Arch == "thumbv7k")
                          ? llvm::ARM::ArchKind::ARMV7K
                          : llvm::ARM::parseCPUArch(CPU);
  }
  return ArchKind;
}

/// getLLVMArchSuffixForARM - Get the LLVM arch name to use for a particular
/// CPU  (or Arch, if CPU is generic).
// FIXME: This is redundant with -mcpu, why does LLVM use this.
StringRef arm::getLLVMArchSuffixForARM(StringRef CPU, StringRef Arch,
                                       const llvm::Triple &Triple) {
  llvm::ARM::ArchKind ArchKind = getLLVMArchKindForARM(CPU, Arch, Triple);
  if (ArchKind == llvm::ARM::ArchKind::INVALID)
    return "";
  return llvm::ARM::getSubArch(ArchKind);
}

void arm::appendBE8LinkFlag(const ArgList &Args, ArgStringList &CmdArgs,
                            const llvm::Triple &Triple) {
  if (Args.hasArg(options::OPT_r))
    return;

  // ARMv7 (and later) and ARMv6-M do not support BE-32, so instruct the linker
  // to generate BE-8 executables.
  if (arm::getARMSubArchVersionNumber(Triple) >= 7 || arm::isARMMProfile(Triple))
    CmdArgs.push_back("--be8");
}