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
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
| //===- lib/MC/MCAssembler.cpp - Assembler Backend Implementation ----------===//
//
// 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 "llvm/MC/MCAssembler.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/Twine.h"
#include "llvm/MC/MCAsmBackend.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCAsmLayout.h"
#include "llvm/MC/MCCodeEmitter.h"
#include "llvm/MC/MCCodeView.h"
#include "llvm/MC/MCContext.h"
#include "llvm/MC/MCDwarf.h"
#include "llvm/MC/MCExpr.h"
#include "llvm/MC/MCFixup.h"
#include "llvm/MC/MCFixupKindInfo.h"
#include "llvm/MC/MCFragment.h"
#include "llvm/MC/MCInst.h"
#include "llvm/MC/MCObjectWriter.h"
#include "llvm/MC/MCSection.h"
#include "llvm/MC/MCSectionELF.h"
#include "llvm/MC/MCSymbol.h"
#include "llvm/MC/MCValue.h"
#include "llvm/Support/Alignment.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/LEB128.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/raw_ostream.h"
#include <cassert>
#include <cstdint>
#include <cstring>
#include <tuple>
#include <utility>
using namespace llvm;
#define DEBUG_TYPE "assembler"
namespace {
namespace stats {
STATISTIC(EmittedFragments, "Number of emitted assembler fragments - total");
STATISTIC(EmittedRelaxableFragments,
"Number of emitted assembler fragments - relaxable");
STATISTIC(EmittedDataFragments,
"Number of emitted assembler fragments - data");
STATISTIC(EmittedCompactEncodedInstFragments,
"Number of emitted assembler fragments - compact encoded inst");
STATISTIC(EmittedAlignFragments,
"Number of emitted assembler fragments - align");
STATISTIC(EmittedFillFragments,
"Number of emitted assembler fragments - fill");
STATISTIC(EmittedOrgFragments,
"Number of emitted assembler fragments - org");
STATISTIC(evaluateFixup, "Number of evaluated fixups");
STATISTIC(FragmentLayouts, "Number of fragment layouts");
STATISTIC(ObjectBytes, "Number of emitted object file bytes");
STATISTIC(RelaxationSteps, "Number of assembler layout and relaxation steps");
STATISTIC(RelaxedInstructions, "Number of relaxed instructions");
STATISTIC(PaddingFragmentsRelaxations,
"Number of Padding Fragments relaxations");
STATISTIC(PaddingFragmentsBytes,
"Total size of all padding from adding Fragments");
} // end namespace stats
} // end anonymous namespace
// FIXME FIXME FIXME: There are number of places in this file where we convert
// what is a 64-bit assembler value used for computation into a value in the
// object file, which may truncate it. We should detect that truncation where
// invalid and report errors back.
/* *** */
MCAssembler::MCAssembler(MCContext &Context,
std::unique_ptr<MCAsmBackend> Backend,
std::unique_ptr<MCCodeEmitter> Emitter,
std::unique_ptr<MCObjectWriter> Writer)
: Context(Context), Backend(std::move(Backend)),
Emitter(std::move(Emitter)), Writer(std::move(Writer)),
BundleAlignSize(0), RelaxAll(false), SubsectionsViaSymbols(false),
IncrementalLinkerCompatible(false), ELFHeaderEFlags(0) {
VersionInfo.Major = 0; // Major version == 0 for "none specified"
}
MCAssembler::~MCAssembler() = default;
void MCAssembler::reset() {
Sections.clear();
Symbols.clear();
IndirectSymbols.clear();
DataRegions.clear();
LinkerOptions.clear();
FileNames.clear();
ThumbFuncs.clear();
BundleAlignSize = 0;
RelaxAll = false;
SubsectionsViaSymbols = false;
IncrementalLinkerCompatible = false;
ELFHeaderEFlags = 0;
LOHContainer.reset();
VersionInfo.Major = 0;
VersionInfo.SDKVersion = VersionTuple();
// reset objects owned by us
if (getBackendPtr())
getBackendPtr()->reset();
if (getEmitterPtr())
getEmitterPtr()->reset();
if (getWriterPtr())
getWriterPtr()->reset();
getLOHContainer().reset();
}
bool MCAssembler::registerSection(MCSection &Section) {
if (Section.isRegistered())
return false;
Sections.push_back(&Section);
Section.setIsRegistered(true);
return true;
}
bool MCAssembler::isThumbFunc(const MCSymbol *Symbol) const {
if (ThumbFuncs.count(Symbol))
return true;
if (!Symbol->isVariable())
return false;
const MCExpr *Expr = Symbol->getVariableValue();
MCValue V;
if (!Expr->evaluateAsRelocatable(V, nullptr, nullptr))
return false;
if (V.getSymB() || V.getRefKind() != MCSymbolRefExpr::VK_None)
return false;
const MCSymbolRefExpr *Ref = V.getSymA();
if (!Ref)
return false;
if (Ref->getKind() != MCSymbolRefExpr::VK_None)
return false;
const MCSymbol &Sym = Ref->getSymbol();
if (!isThumbFunc(&Sym))
return false;
ThumbFuncs.insert(Symbol); // Cache it.
return true;
}
bool MCAssembler::isSymbolLinkerVisible(const MCSymbol &Symbol) const {
// Non-temporary labels should always be visible to the linker.
if (!Symbol.isTemporary())
return true;
// Absolute temporary labels are never visible.
if (!Symbol.isInSection())
return false;
if (Symbol.isUsedInReloc())
return true;
return false;
}
const MCSymbol *MCAssembler::getAtom(const MCSymbol &S) const {
// Linker visible symbols define atoms.
if (isSymbolLinkerVisible(S))
return &S;
// Absolute and undefined symbols have no defining atom.
if (!S.isInSection())
return nullptr;
// Non-linker visible symbols in sections which can't be atomized have no
// defining atom.
if (!getContext().getAsmInfo()->isSectionAtomizableBySymbols(
*S.getFragment()->getParent()))
return nullptr;
// Otherwise, return the atom for the containing fragment.
return S.getFragment()->getAtom();
}
bool MCAssembler::evaluateFixup(const MCAsmLayout &Layout,
const MCFixup &Fixup, const MCFragment *DF,
MCValue &Target, uint64_t &Value,
bool &WasForced) const {
++stats::evaluateFixup;
// FIXME: This code has some duplication with recordRelocation. We should
// probably merge the two into a single callback that tries to evaluate a
// fixup and records a relocation if one is needed.
// On error claim to have completely evaluated the fixup, to prevent any
// further processing from being done.
const MCExpr *Expr = Fixup.getValue();
MCContext &Ctx = getContext();
Value = 0;
WasForced = false;
if (!Expr->evaluateAsRelocatable(Target, &Layout, &Fixup)) {
Ctx.reportError(Fixup.getLoc(), "expected relocatable expression");
return true;
}
if (const MCSymbolRefExpr *RefB = Target.getSymB()) {
if (RefB->getKind() != MCSymbolRefExpr::VK_None) {
Ctx.reportError(Fixup.getLoc(),
"unsupported subtraction of qualified symbol");
return true;
}
}
assert(getBackendPtr() && "Expected assembler backend");
bool IsPCRel = getBackendPtr()->getFixupKindInfo(Fixup.getKind()).Flags &
MCFixupKindInfo::FKF_IsPCRel;
bool IsResolved = false;
if (IsPCRel) {
if (Target.getSymB()) {
IsResolved = false;
} else if (!Target.getSymA()) {
IsResolved = false;
} else {
const MCSymbolRefExpr *A = Target.getSymA();
const MCSymbol &SA = A->getSymbol();
if (A->getKind() != MCSymbolRefExpr::VK_None || SA.isUndefined()) {
IsResolved = false;
} else if (auto *Writer = getWriterPtr()) {
IsResolved = Writer->isSymbolRefDifferenceFullyResolvedImpl(
*this, SA, *DF, false, true);
}
}
} else {
IsResolved = Target.isAbsolute();
}
Value = Target.getConstant();
if (const MCSymbolRefExpr *A = Target.getSymA()) {
const MCSymbol &Sym = A->getSymbol();
if (Sym.isDefined())
Value += Layout.getSymbolOffset(Sym);
}
if (const MCSymbolRefExpr *B = Target.getSymB()) {
const MCSymbol &Sym = B->getSymbol();
if (Sym.isDefined())
Value -= Layout.getSymbolOffset(Sym);
}
bool ShouldAlignPC = getBackend().getFixupKindInfo(Fixup.getKind()).Flags &
MCFixupKindInfo::FKF_IsAlignedDownTo32Bits;
assert((ShouldAlignPC ? IsPCRel : true) &&
"FKF_IsAlignedDownTo32Bits is only allowed on PC-relative fixups!");
if (IsPCRel) {
uint32_t Offset = Layout.getFragmentOffset(DF) + Fixup.getOffset();
// A number of ARM fixups in Thumb mode require that the effective PC
// address be determined as the 32-bit aligned version of the actual offset.
if (ShouldAlignPC) Offset &= ~0x3;
Value -= Offset;
}
// Let the backend force a relocation if needed.
if (IsResolved && getBackend().shouldForceRelocation(*this, Fixup, Target)) {
IsResolved = false;
WasForced = true;
}
return IsResolved;
}
uint64_t MCAssembler::computeFragmentSize(const MCAsmLayout &Layout,
const MCFragment &F) const {
assert(getBackendPtr() && "Requires assembler backend");
switch (F.getKind()) {
case MCFragment::FT_Data:
return cast<MCDataFragment>(F).getContents().size();
case MCFragment::FT_Relaxable:
return cast<MCRelaxableFragment>(F).getContents().size();
case MCFragment::FT_CompactEncodedInst:
return cast<MCCompactEncodedInstFragment>(F).getContents().size();
case MCFragment::FT_Fill: {
auto &FF = cast<MCFillFragment>(F);
int64_t NumValues = 0;
if (!FF.getNumValues().evaluateAsAbsolute(NumValues, Layout)) {
getContext().reportError(FF.getLoc(),
"expected assembly-time absolute expression");
return 0;
}
int64_t Size = NumValues * FF.getValueSize();
if (Size < 0) {
getContext().reportError(FF.getLoc(), "invalid number of bytes");
return 0;
}
return Size;
}
case MCFragment::FT_LEB:
return cast<MCLEBFragment>(F).getContents().size();
case MCFragment::FT_Padding:
return cast<MCPaddingFragment>(F).getSize();
case MCFragment::FT_SymbolId:
return 4;
case MCFragment::FT_Align: {
const MCAlignFragment &AF = cast<MCAlignFragment>(F);
unsigned Offset = Layout.getFragmentOffset(&AF);
unsigned Size = offsetToAlignment(Offset, Align(AF.getAlignment()));
// Insert extra Nops for code alignment if the target define
// shouldInsertExtraNopBytesForCodeAlign target hook.
if (AF.getParent()->UseCodeAlign() && AF.hasEmitNops() &&
getBackend().shouldInsertExtraNopBytesForCodeAlign(AF, Size))
return Size;
// If we are padding with nops, force the padding to be larger than the
// minimum nop size.
if (Size > 0 && AF.hasEmitNops()) {
while (Size % getBackend().getMinimumNopSize())
Size += AF.getAlignment();
}
if (Size > AF.getMaxBytesToEmit())
return 0;
return Size;
}
case MCFragment::FT_Org: {
const MCOrgFragment &OF = cast<MCOrgFragment>(F);
MCValue Value;
if (!OF.getOffset().evaluateAsValue(Value, Layout)) {
getContext().reportError(OF.getLoc(),
"expected assembly-time absolute expression");
return 0;
}
uint64_t FragmentOffset = Layout.getFragmentOffset(&OF);
int64_t TargetLocation = Value.getConstant();
if (const MCSymbolRefExpr *A = Value.getSymA()) {
uint64_t Val;
if (!Layout.getSymbolOffset(A->getSymbol(), Val)) {
getContext().reportError(OF.getLoc(), "expected absolute expression");
return 0;
}
TargetLocation += Val;
}
int64_t Size = TargetLocation - FragmentOffset;
if (Size < 0 || Size >= 0x40000000) {
getContext().reportError(
OF.getLoc(), "invalid .org offset '" + Twine(TargetLocation) +
"' (at offset '" + Twine(FragmentOffset) + "')");
return 0;
}
return Size;
}
case MCFragment::FT_Dwarf:
return cast<MCDwarfLineAddrFragment>(F).getContents().size();
case MCFragment::FT_DwarfFrame:
return cast<MCDwarfCallFrameFragment>(F).getContents().size();
case MCFragment::FT_CVInlineLines:
return cast<MCCVInlineLineTableFragment>(F).getContents().size();
case MCFragment::FT_CVDefRange:
return cast<MCCVDefRangeFragment>(F).getContents().size();
case MCFragment::FT_Dummy:
llvm_unreachable("Should not have been added");
}
llvm_unreachable("invalid fragment kind");
}
void MCAsmLayout::layoutFragment(MCFragment *F) {
MCFragment *Prev = F->getPrevNode();
// We should never try to recompute something which is valid.
assert(!isFragmentValid(F) && "Attempt to recompute a valid fragment!");
// We should never try to compute the fragment layout if its predecessor
// isn't valid.
assert((!Prev || isFragmentValid(Prev)) &&
"Attempt to compute fragment before its predecessor!");
++stats::FragmentLayouts;
// Compute fragment offset and size.
if (Prev)
F->Offset = Prev->Offset + getAssembler().computeFragmentSize(*this, *Prev);
else
F->Offset = 0;
LastValidFragment[F->getParent()] = F;
// If bundling is enabled and this fragment has instructions in it, it has to
// obey the bundling restrictions. With padding, we'll have:
//
//
// BundlePadding
// |||
// -------------------------------------
// Prev |##########| F |
// -------------------------------------
// ^
// |
// F->Offset
//
// The fragment's offset will point to after the padding, and its computed
// size won't include the padding.
//
// When the -mc-relax-all flag is used, we optimize bundling by writting the
// padding directly into fragments when the instructions are emitted inside
// the streamer. When the fragment is larger than the bundle size, we need to
// ensure that it's bundle aligned. This means that if we end up with
// multiple fragments, we must emit bundle padding between fragments.
//
// ".align N" is an example of a directive that introduces multiple
// fragments. We could add a special case to handle ".align N" by emitting
// within-fragment padding (which would produce less padding when N is less
// than the bundle size), but for now we don't.
//
if (Assembler.isBundlingEnabled() && F->hasInstructions()) {
assert(isa<MCEncodedFragment>(F) &&
"Only MCEncodedFragment implementations have instructions");
MCEncodedFragment *EF = cast<MCEncodedFragment>(F);
uint64_t FSize = Assembler.computeFragmentSize(*this, *EF);
if (!Assembler.getRelaxAll() && FSize > Assembler.getBundleAlignSize())
report_fatal_error("Fragment can't be larger than a bundle size");
uint64_t RequiredBundlePadding =
computeBundlePadding(Assembler, EF, EF->Offset, FSize);
if (RequiredBundlePadding > UINT8_MAX)
report_fatal_error("Padding cannot exceed 255 bytes");
EF->setBundlePadding(static_cast<uint8_t>(RequiredBundlePadding));
EF->Offset += RequiredBundlePadding;
}
}
void MCAssembler::registerSymbol(const MCSymbol &Symbol, bool *Created) {
bool New = !Symbol.isRegistered();
if (Created)
*Created = New;
if (New) {
Symbol.setIsRegistered(true);
Symbols.push_back(&Symbol);
}
}
void MCAssembler::writeFragmentPadding(raw_ostream &OS,
const MCEncodedFragment &EF,
uint64_t FSize) const {
assert(getBackendPtr() && "Expected assembler backend");
// Should NOP padding be written out before this fragment?
unsigned BundlePadding = EF.getBundlePadding();
if (BundlePadding > 0) {
assert(isBundlingEnabled() &&
"Writing bundle padding with disabled bundling");
assert(EF.hasInstructions() &&
"Writing bundle padding for a fragment without instructions");
unsigned TotalLength = BundlePadding + static_cast<unsigned>(FSize);
if (EF.alignToBundleEnd() && TotalLength > getBundleAlignSize()) {
// If the padding itself crosses a bundle boundary, it must be emitted
// in 2 pieces, since even nop instructions must not cross boundaries.
// v--------------v <- BundleAlignSize
// v---------v <- BundlePadding
// ----------------------------
// | Prev |####|####| F |
// ----------------------------
// ^-------------------^ <- TotalLength
unsigned DistanceToBoundary = TotalLength - getBundleAlignSize();
if (!getBackend().writeNopData(OS, DistanceToBoundary))
report_fatal_error("unable to write NOP sequence of " +
Twine(DistanceToBoundary) + " bytes");
BundlePadding -= DistanceToBoundary;
}
if (!getBackend().writeNopData(OS, BundlePadding))
report_fatal_error("unable to write NOP sequence of " +
Twine(BundlePadding) + " bytes");
}
}
/// Write the fragment \p F to the output file.
static void writeFragment(raw_ostream &OS, const MCAssembler &Asm,
const MCAsmLayout &Layout, const MCFragment &F) {
// FIXME: Embed in fragments instead?
uint64_t FragmentSize = Asm.computeFragmentSize(Layout, F);
support::endianness Endian = Asm.getBackend().Endian;
if (const MCEncodedFragment *EF = dyn_cast<MCEncodedFragment>(&F))
Asm.writeFragmentPadding(OS, *EF, FragmentSize);
// This variable (and its dummy usage) is to participate in the assert at
// the end of the function.
uint64_t Start = OS.tell();
(void) Start;
++stats::EmittedFragments;
switch (F.getKind()) {
case MCFragment::FT_Align: {
++stats::EmittedAlignFragments;
const MCAlignFragment &AF = cast<MCAlignFragment>(F);
assert(AF.getValueSize() && "Invalid virtual align in concrete fragment!");
uint64_t Count = FragmentSize / AF.getValueSize();
// FIXME: This error shouldn't actually occur (the front end should emit
// multiple .align directives to enforce the semantics it wants), but is
// severe enough that we want to report it. How to handle this?
if (Count * AF.getValueSize() != FragmentSize)
report_fatal_error("undefined .align directive, value size '" +
Twine(AF.getValueSize()) +
"' is not a divisor of padding size '" +
Twine(FragmentSize) + "'");
// See if we are aligning with nops, and if so do that first to try to fill
// the Count bytes. Then if that did not fill any bytes or there are any
// bytes left to fill use the Value and ValueSize to fill the rest.
// If we are aligning with nops, ask that target to emit the right data.
if (AF.hasEmitNops()) {
if (!Asm.getBackend().writeNopData(OS, Count))
report_fatal_error("unable to write nop sequence of " +
Twine(Count) + " bytes");
break;
}
// Otherwise, write out in multiples of the value size.
for (uint64_t i = 0; i != Count; ++i) {
switch (AF.getValueSize()) {
default: llvm_unreachable("Invalid size!");
case 1: OS << char(AF.getValue()); break;
case 2:
support::endian::write<uint16_t>(OS, AF.getValue(), Endian);
break;
case 4:
support::endian::write<uint32_t>(OS, AF.getValue(), Endian);
break;
case 8:
support::endian::write<uint64_t>(OS, AF.getValue(), Endian);
break;
}
}
break;
}
case MCFragment::FT_Data:
++stats::EmittedDataFragments;
OS << cast<MCDataFragment>(F).getContents();
break;
case MCFragment::FT_Relaxable:
++stats::EmittedRelaxableFragments;
OS << cast<MCRelaxableFragment>(F).getContents();
break;
case MCFragment::FT_CompactEncodedInst:
++stats::EmittedCompactEncodedInstFragments;
OS << cast<MCCompactEncodedInstFragment>(F).getContents();
break;
case MCFragment::FT_Fill: {
++stats::EmittedFillFragments;
const MCFillFragment &FF = cast<MCFillFragment>(F);
uint64_t V = FF.getValue();
unsigned VSize = FF.getValueSize();
const unsigned MaxChunkSize = 16;
char Data[MaxChunkSize];
// Duplicate V into Data as byte vector to reduce number of
// writes done. As such, do endian conversion here.
for (unsigned I = 0; I != VSize; ++I) {
unsigned index = Endian == support::little ? I : (VSize - I - 1);
Data[I] = uint8_t(V >> (index * 8));
}
for (unsigned I = VSize; I < MaxChunkSize; ++I)
Data[I] = Data[I - VSize];
// Set to largest multiple of VSize in Data.
const unsigned NumPerChunk = MaxChunkSize / VSize;
// Set ChunkSize to largest multiple of VSize in Data
const unsigned ChunkSize = VSize * NumPerChunk;
// Do copies by chunk.
StringRef Ref(Data, ChunkSize);
for (uint64_t I = 0, E = FragmentSize / ChunkSize; I != E; ++I)
OS << Ref;
// do remainder if needed.
unsigned TrailingCount = FragmentSize % ChunkSize;
if (TrailingCount)
OS.write(Data, TrailingCount);
break;
}
case MCFragment::FT_LEB: {
const MCLEBFragment &LF = cast<MCLEBFragment>(F);
OS << LF.getContents();
break;
}
case MCFragment::FT_Padding: {
if (!Asm.getBackend().writeNopData(OS, FragmentSize))
report_fatal_error("unable to write nop sequence of " +
Twine(FragmentSize) + " bytes");
break;
}
case MCFragment::FT_SymbolId: {
const MCSymbolIdFragment &SF = cast<MCSymbolIdFragment>(F);
support::endian::write<uint32_t>(OS, SF.getSymbol()->getIndex(), Endian);
break;
}
case MCFragment::FT_Org: {
++stats::EmittedOrgFragments;
const MCOrgFragment &OF = cast<MCOrgFragment>(F);
for (uint64_t i = 0, e = FragmentSize; i != e; ++i)
OS << char(OF.getValue());
break;
}
case MCFragment::FT_Dwarf: {
const MCDwarfLineAddrFragment &OF = cast<MCDwarfLineAddrFragment>(F);
OS << OF.getContents();
break;
}
case MCFragment::FT_DwarfFrame: {
const MCDwarfCallFrameFragment &CF = cast<MCDwarfCallFrameFragment>(F);
OS << CF.getContents();
break;
}
case MCFragment::FT_CVInlineLines: {
const auto &OF = cast<MCCVInlineLineTableFragment>(F);
OS << OF.getContents();
break;
}
case MCFragment::FT_CVDefRange: {
const auto &DRF = cast<MCCVDefRangeFragment>(F);
OS << DRF.getContents();
break;
}
case MCFragment::FT_Dummy:
llvm_unreachable("Should not have been added");
}
assert(OS.tell() - Start == FragmentSize &&
"The stream should advance by fragment size");
}
void MCAssembler::writeSectionData(raw_ostream &OS, const MCSection *Sec,
const MCAsmLayout &Layout) const {
assert(getBackendPtr() && "Expected assembler backend");
// Ignore virtual sections.
if (Sec->isVirtualSection()) {
assert(Layout.getSectionFileSize(Sec) == 0 && "Invalid size for section!");
// Check that contents are only things legal inside a virtual section.
for (const MCFragment &F : *Sec) {
switch (F.getKind()) {
default: llvm_unreachable("Invalid fragment in virtual section!");
case MCFragment::FT_Data: {
// Check that we aren't trying to write a non-zero contents (or fixups)
// into a virtual section. This is to support clients which use standard
// directives to fill the contents of virtual sections.
const MCDataFragment &DF = cast<MCDataFragment>(F);
if (DF.fixup_begin() != DF.fixup_end())
report_fatal_error("cannot have fixups in virtual section!");
for (unsigned i = 0, e = DF.getContents().size(); i != e; ++i)
if (DF.getContents()[i]) {
if (auto *ELFSec = dyn_cast<const MCSectionELF>(Sec))
report_fatal_error("non-zero initializer found in section '" +
ELFSec->getSectionName() + "'");
else
report_fatal_error("non-zero initializer found in virtual section");
}
break;
}
case MCFragment::FT_Align:
// Check that we aren't trying to write a non-zero value into a virtual
// section.
assert((cast<MCAlignFragment>(F).getValueSize() == 0 ||
cast<MCAlignFragment>(F).getValue() == 0) &&
"Invalid align in virtual section!");
break;
case MCFragment::FT_Fill:
assert((cast<MCFillFragment>(F).getValue() == 0) &&
"Invalid fill in virtual section!");
break;
}
}
return;
}
uint64_t Start = OS.tell();
(void)Start;
for (const MCFragment &F : *Sec)
writeFragment(OS, *this, Layout, F);
assert(OS.tell() - Start == Layout.getSectionAddressSize(Sec));
}
std::tuple<MCValue, uint64_t, bool>
MCAssembler::handleFixup(const MCAsmLayout &Layout, MCFragment &F,
const MCFixup &Fixup) {
// Evaluate the fixup.
MCValue Target;
uint64_t FixedValue;
bool WasForced;
bool IsResolved = evaluateFixup(Layout, Fixup, &F, Target, FixedValue,
WasForced);
if (!IsResolved) {
// The fixup was unresolved, we need a relocation. Inform the object
// writer of the relocation, and give it an opportunity to adjust the
// fixup value if need be.
if (Target.getSymA() && Target.getSymB() &&
getBackend().requiresDiffExpressionRelocations()) {
// The fixup represents the difference between two symbols, which the
// backend has indicated must be resolved at link time. Split up the fixup
// into two relocations, one for the add, and one for the sub, and emit
// both of these. The constant will be associated with the add half of the
// expression.
MCFixup FixupAdd = MCFixup::createAddFor(Fixup);
MCValue TargetAdd =
MCValue::get(Target.getSymA(), nullptr, Target.getConstant());
getWriter().recordRelocation(*this, Layout, &F, FixupAdd, TargetAdd,
FixedValue);
MCFixup FixupSub = MCFixup::createSubFor(Fixup);
MCValue TargetSub = MCValue::get(Target.getSymB());
getWriter().recordRelocation(*this, Layout, &F, FixupSub, TargetSub,
FixedValue);
} else {
getWriter().recordRelocation(*this, Layout, &F, Fixup, Target,
FixedValue);
}
}
return std::make_tuple(Target, FixedValue, IsResolved);
}
void MCAssembler::layout(MCAsmLayout &Layout) {
assert(getBackendPtr() && "Expected assembler backend");
DEBUG_WITH_TYPE("mc-dump", {
errs() << "assembler backend - pre-layout\n--\n";
dump(); });
// Create dummy fragments and assign section ordinals.
unsigned SectionIndex = 0;
for (MCSection &Sec : *this) {
// Create dummy fragments to eliminate any empty sections, this simplifies
// layout.
if (Sec.getFragmentList().empty())
new MCDataFragment(&Sec);
Sec.setOrdinal(SectionIndex++);
}
// Assign layout order indices to sections and fragments.
for (unsigned i = 0, e = Layout.getSectionOrder().size(); i != e; ++i) {
MCSection *Sec = Layout.getSectionOrder()[i];
Sec->setLayoutOrder(i);
unsigned FragmentIndex = 0;
for (MCFragment &Frag : *Sec)
Frag.setLayoutOrder(FragmentIndex++);
}
// Layout until everything fits.
while (layoutOnce(Layout))
if (getContext().hadError())
return;
DEBUG_WITH_TYPE("mc-dump", {
errs() << "assembler backend - post-relaxation\n--\n";
dump(); });
// Finalize the layout, including fragment lowering.
finishLayout(Layout);
DEBUG_WITH_TYPE("mc-dump", {
errs() << "assembler backend - final-layout\n--\n";
dump(); });
// Allow the object writer a chance to perform post-layout binding (for
// example, to set the index fields in the symbol data).
getWriter().executePostLayoutBinding(*this, Layout);
// Evaluate and apply the fixups, generating relocation entries as necessary.
for (MCSection &Sec : *this) {
for (MCFragment &Frag : Sec) {
// Data and relaxable fragments both have fixups. So only process
// those here.
// FIXME: Is there a better way to do this? MCEncodedFragmentWithFixups
// being templated makes this tricky.
if (isa<MCEncodedFragment>(&Frag) &&
isa<MCCompactEncodedInstFragment>(&Frag))
continue;
if (!isa<MCEncodedFragment>(&Frag) && !isa<MCCVDefRangeFragment>(&Frag) &&
!isa<MCAlignFragment>(&Frag))
continue;
ArrayRef<MCFixup> Fixups;
MutableArrayRef<char> Contents;
const MCSubtargetInfo *STI = nullptr;
if (auto *FragWithFixups = dyn_cast<MCDataFragment>(&Frag)) {
Fixups = FragWithFixups->getFixups();
Contents = FragWithFixups->getContents();
STI = FragWithFixups->getSubtargetInfo();
assert(!FragWithFixups->hasInstructions() || STI != nullptr);
} else if (auto *FragWithFixups = dyn_cast<MCRelaxableFragment>(&Frag)) {
Fixups = FragWithFixups->getFixups();
Contents = FragWithFixups->getContents();
STI = FragWithFixups->getSubtargetInfo();
assert(!FragWithFixups->hasInstructions() || STI != nullptr);
} else if (auto *FragWithFixups = dyn_cast<MCCVDefRangeFragment>(&Frag)) {
Fixups = FragWithFixups->getFixups();
Contents = FragWithFixups->getContents();
} else if (auto *FragWithFixups = dyn_cast<MCDwarfLineAddrFragment>(&Frag)) {
Fixups = FragWithFixups->getFixups();
Contents = FragWithFixups->getContents();
} else if (auto *AF = dyn_cast<MCAlignFragment>(&Frag)) {
// Insert fixup type for code alignment if the target define
// shouldInsertFixupForCodeAlign target hook.
if (Sec.UseCodeAlign() && AF->hasEmitNops()) {
getBackend().shouldInsertFixupForCodeAlign(*this, Layout, *AF);
}
continue;
} else if (auto *FragWithFixups =
dyn_cast<MCDwarfCallFrameFragment>(&Frag)) {
Fixups = FragWithFixups->getFixups();
Contents = FragWithFixups->getContents();
} else
llvm_unreachable("Unknown fragment with fixups!");
for (const MCFixup &Fixup : Fixups) {
uint64_t FixedValue;
bool IsResolved;
MCValue Target;
std::tie(Target, FixedValue, IsResolved) =
handleFixup(Layout, Frag, Fixup);
getBackend().applyFixup(*this, Fixup, Target, Contents, FixedValue,
IsResolved, STI);
}
}
}
}
void MCAssembler::Finish() {
// Create the layout object.
MCAsmLayout Layout(*this);
layout(Layout);
// Write the object file.
stats::ObjectBytes += getWriter().writeObject(*this, Layout);
}
bool MCAssembler::fixupNeedsRelaxation(const MCFixup &Fixup,
const MCRelaxableFragment *DF,
const MCAsmLayout &Layout) const {
assert(getBackendPtr() && "Expected assembler backend");
MCValue Target;
uint64_t Value;
bool WasForced;
bool Resolved = evaluateFixup(Layout, Fixup, DF, Target, Value, WasForced);
if (Target.getSymA() &&
Target.getSymA()->getKind() == MCSymbolRefExpr::VK_X86_ABS8 &&
Fixup.getKind() == FK_Data_1)
return false;
return getBackend().fixupNeedsRelaxationAdvanced(Fixup, Resolved, Value, DF,
Layout, WasForced);
}
bool MCAssembler::fragmentNeedsRelaxation(const MCRelaxableFragment *F,
const MCAsmLayout &Layout) const {
assert(getBackendPtr() && "Expected assembler backend");
// If this inst doesn't ever need relaxation, ignore it. This occurs when we
// are intentionally pushing out inst fragments, or because we relaxed a
// previous instruction to one that doesn't need relaxation.
if (!getBackend().mayNeedRelaxation(F->getInst(), *F->getSubtargetInfo()))
return false;
for (const MCFixup &Fixup : F->getFixups())
if (fixupNeedsRelaxation(Fixup, F, Layout))
return true;
return false;
}
bool MCAssembler::relaxInstruction(MCAsmLayout &Layout,
MCRelaxableFragment &F) {
assert(getEmitterPtr() &&
"Expected CodeEmitter defined for relaxInstruction");
if (!fragmentNeedsRelaxation(&F, Layout))
return false;
++stats::RelaxedInstructions;
// FIXME-PERF: We could immediately lower out instructions if we can tell
// they are fully resolved, to avoid retesting on later passes.
// Relax the fragment.
MCInst Relaxed;
getBackend().relaxInstruction(F.getInst(), *F.getSubtargetInfo(), Relaxed);
// Encode the new instruction.
//
// FIXME-PERF: If it matters, we could let the target do this. It can
// probably do so more efficiently in many cases.
SmallVector<MCFixup, 4> Fixups;
SmallString<256> Code;
raw_svector_ostream VecOS(Code);
getEmitter().encodeInstruction(Relaxed, VecOS, Fixups, *F.getSubtargetInfo());
// Update the fragment.
F.setInst(Relaxed);
F.getContents() = Code;
F.getFixups() = Fixups;
return true;
}
bool MCAssembler::relaxPaddingFragment(MCAsmLayout &Layout,
MCPaddingFragment &PF) {
assert(getBackendPtr() && "Expected assembler backend");
uint64_t OldSize = PF.getSize();
if (!getBackend().relaxFragment(&PF, Layout))
return false;
uint64_t NewSize = PF.getSize();
++stats::PaddingFragmentsRelaxations;
stats::PaddingFragmentsBytes += NewSize;
stats::PaddingFragmentsBytes -= OldSize;
return true;
}
bool MCAssembler::relaxLEB(MCAsmLayout &Layout, MCLEBFragment &LF) {
uint64_t OldSize = LF.getContents().size();
int64_t Value;
bool Abs = LF.getValue().evaluateKnownAbsolute(Value, Layout);
if (!Abs)
report_fatal_error("sleb128 and uleb128 expressions must be absolute");
SmallString<8> &Data = LF.getContents();
Data.clear();
raw_svector_ostream OSE(Data);
// The compiler can generate EH table assembly that is impossible to assemble
// without either adding padding to an LEB fragment or adding extra padding
// to a later alignment fragment. To accommodate such tables, relaxation can
// only increase an LEB fragment size here, not decrease it. See PR35809.
if (LF.isSigned())
encodeSLEB128(Value, OSE, OldSize);
else
encodeULEB128(Value, OSE, OldSize);
return OldSize != LF.getContents().size();
}
bool MCAssembler::relaxDwarfLineAddr(MCAsmLayout &Layout,
MCDwarfLineAddrFragment &DF) {
MCContext &Context = Layout.getAssembler().getContext();
uint64_t OldSize = DF.getContents().size();
int64_t AddrDelta;
bool Abs = DF.getAddrDelta().evaluateKnownAbsolute(AddrDelta, Layout);
assert(Abs && "We created a line delta with an invalid expression");
(void)Abs;
int64_t LineDelta;
LineDelta = DF.getLineDelta();
SmallVectorImpl<char> &Data = DF.getContents();
Data.clear();
raw_svector_ostream OSE(Data);
DF.getFixups().clear();
if (!getBackend().requiresDiffExpressionRelocations()) {
MCDwarfLineAddr::Encode(Context, getDWARFLinetableParams(), LineDelta,
AddrDelta, OSE);
} else {
uint32_t Offset;
uint32_t Size;
bool SetDelta = MCDwarfLineAddr::FixedEncode(Context,
getDWARFLinetableParams(),
LineDelta, AddrDelta,
OSE, &Offset, &Size);
// Add Fixups for address delta or new address.
const MCExpr *FixupExpr;
if (SetDelta) {
FixupExpr = &DF.getAddrDelta();
} else {
const MCBinaryExpr *ABE = cast<MCBinaryExpr>(&DF.getAddrDelta());
FixupExpr = ABE->getLHS();
}
DF.getFixups().push_back(
MCFixup::create(Offset, FixupExpr,
MCFixup::getKindForSize(Size, false /*isPCRel*/)));
}
return OldSize != Data.size();
}
bool MCAssembler::relaxDwarfCallFrameFragment(MCAsmLayout &Layout,
MCDwarfCallFrameFragment &DF) {
MCContext &Context = Layout.getAssembler().getContext();
uint64_t OldSize = DF.getContents().size();
int64_t AddrDelta;
bool Abs = DF.getAddrDelta().evaluateKnownAbsolute(AddrDelta, Layout);
assert(Abs && "We created call frame with an invalid expression");
(void) Abs;
SmallVectorImpl<char> &Data = DF.getContents();
Data.clear();
raw_svector_ostream OSE(Data);
DF.getFixups().clear();
if (getBackend().requiresDiffExpressionRelocations()) {
uint32_t Offset;
uint32_t Size;
MCDwarfFrameEmitter::EncodeAdvanceLoc(Context, AddrDelta, OSE, &Offset,
&Size);
if (Size) {
DF.getFixups().push_back(MCFixup::create(
Offset, &DF.getAddrDelta(),
MCFixup::getKindForSizeInBits(Size /*In bits.*/, false /*isPCRel*/)));
}
} else {
MCDwarfFrameEmitter::EncodeAdvanceLoc(Context, AddrDelta, OSE);
}
return OldSize != Data.size();
}
bool MCAssembler::relaxCVInlineLineTable(MCAsmLayout &Layout,
MCCVInlineLineTableFragment &F) {
unsigned OldSize = F.getContents().size();
getContext().getCVContext().encodeInlineLineTable(Layout, F);
return OldSize != F.getContents().size();
}
bool MCAssembler::relaxCVDefRange(MCAsmLayout &Layout,
MCCVDefRangeFragment &F) {
unsigned OldSize = F.getContents().size();
getContext().getCVContext().encodeDefRange(Layout, F);
return OldSize != F.getContents().size();
}
bool MCAssembler::layoutSectionOnce(MCAsmLayout &Layout, MCSection &Sec) {
// Holds the first fragment which needed relaxing during this layout. It will
// remain NULL if none were relaxed.
// When a fragment is relaxed, all the fragments following it should get
// invalidated because their offset is going to change.
MCFragment *FirstRelaxedFragment = nullptr;
// Attempt to relax all the fragments in the section.
for (MCSection::iterator I = Sec.begin(), IE = Sec.end(); I != IE; ++I) {
// Check if this is a fragment that needs relaxation.
bool RelaxedFrag = false;
switch(I->getKind()) {
default:
break;
case MCFragment::FT_Relaxable:
assert(!getRelaxAll() &&
"Did not expect a MCRelaxableFragment in RelaxAll mode");
RelaxedFrag = relaxInstruction(Layout, *cast<MCRelaxableFragment>(I));
break;
case MCFragment::FT_Dwarf:
RelaxedFrag = relaxDwarfLineAddr(Layout,
*cast<MCDwarfLineAddrFragment>(I));
break;
case MCFragment::FT_DwarfFrame:
RelaxedFrag =
relaxDwarfCallFrameFragment(Layout,
*cast<MCDwarfCallFrameFragment>(I));
break;
case MCFragment::FT_LEB:
RelaxedFrag = relaxLEB(Layout, *cast<MCLEBFragment>(I));
break;
case MCFragment::FT_Padding:
RelaxedFrag = relaxPaddingFragment(Layout, *cast<MCPaddingFragment>(I));
break;
case MCFragment::FT_CVInlineLines:
RelaxedFrag =
relaxCVInlineLineTable(Layout, *cast<MCCVInlineLineTableFragment>(I));
break;
case MCFragment::FT_CVDefRange:
RelaxedFrag = relaxCVDefRange(Layout, *cast<MCCVDefRangeFragment>(I));
break;
}
if (RelaxedFrag && !FirstRelaxedFragment)
FirstRelaxedFragment = &*I;
}
if (FirstRelaxedFragment) {
Layout.invalidateFragmentsFrom(FirstRelaxedFragment);
return true;
}
return false;
}
bool MCAssembler::layoutOnce(MCAsmLayout &Layout) {
++stats::RelaxationSteps;
bool WasRelaxed = false;
for (iterator it = begin(), ie = end(); it != ie; ++it) {
MCSection &Sec = *it;
while (layoutSectionOnce(Layout, Sec))
WasRelaxed = true;
}
return WasRelaxed;
}
void MCAssembler::finishLayout(MCAsmLayout &Layout) {
assert(getBackendPtr() && "Expected assembler backend");
// The layout is done. Mark every fragment as valid.
for (unsigned int i = 0, n = Layout.getSectionOrder().size(); i != n; ++i) {
MCSection &Section = *Layout.getSectionOrder()[i];
Layout.getFragmentOffset(&*Section.rbegin());
computeFragmentSize(Layout, *Section.rbegin());
}
getBackend().finishLayout(*this, Layout);
}
#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
LLVM_DUMP_METHOD void MCAssembler::dump() const{
raw_ostream &OS = errs();
OS << "<MCAssembler\n";
OS << " Sections:[\n ";
for (const_iterator it = begin(), ie = end(); it != ie; ++it) {
if (it != begin()) OS << ",\n ";
it->dump();
}
OS << "],\n";
OS << " Symbols:[";
for (const_symbol_iterator it = symbol_begin(), ie = symbol_end(); it != ie; ++it) {
if (it != symbol_begin()) OS << ",\n ";
OS << "(";
it->dump();
OS << ", Index:" << it->getIndex() << ", ";
OS << ")";
}
OS << "]>\n";
}
#endif
|