forked from llvm/llvm-project
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathSampleProfReader.cpp
1900 lines (1654 loc) · 62.4 KB
/
SampleProfReader.cpp
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
//===- SampleProfReader.cpp - Read LLVM sample profile data ---------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file implements the class that reads LLVM sample profiles. It
// supports three file formats: text, binary and gcov.
//
// The textual representation is useful for debugging and testing purposes. The
// binary representation is more compact, resulting in smaller file sizes.
//
// The gcov encoding is the one generated by GCC's AutoFDO profile creation
// tool (https://github.com/google/autofdo)
//
// All three encodings can be used interchangeably as an input sample profile.
//
//===----------------------------------------------------------------------===//
#include "llvm/ProfileData/SampleProfReader.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/IR/ProfileSummary.h"
#include "llvm/ProfileData/ProfileCommon.h"
#include "llvm/ProfileData/SampleProf.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Compression.h"
#include "llvm/Support/ErrorOr.h"
#include "llvm/Support/LEB128.h"
#include "llvm/Support/LineIterator.h"
#include "llvm/Support/MD5.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
#include <cstddef>
#include <cstdint>
#include <limits>
#include <memory>
#include <set>
#include <system_error>
#include <vector>
using namespace llvm;
using namespace sampleprof;
#define DEBUG_TYPE "samplepgo-reader"
// This internal option specifies if the profile uses FS discriminators.
// It only applies to text, binary and compact binary format profiles.
// For ext-binary format profiles, the flag is set in the summary.
static cl::opt<bool> ProfileIsFSDisciminator(
"profile-isfs", cl::Hidden, cl::init(false),
cl::desc("Profile uses flow sensitive discriminators"));
/// Dump the function profile for \p FName.
///
/// \param FContext Name + context of the function to print.
/// \param OS Stream to emit the output to.
void SampleProfileReader::dumpFunctionProfile(SampleContext FContext,
raw_ostream &OS) {
OS << "Function: " << FContext.toString() << ": " << Profiles[FContext];
}
/// Dump all the function profiles found on stream \p OS.
void SampleProfileReader::dump(raw_ostream &OS) {
std::vector<NameFunctionSamples> V;
sortFuncProfiles(Profiles, V);
for (const auto &I : V)
dumpFunctionProfile(I.first, OS);
}
/// Parse \p Input as function head.
///
/// Parse one line of \p Input, and update function name in \p FName,
/// function's total sample count in \p NumSamples, function's entry
/// count in \p NumHeadSamples.
///
/// \returns true if parsing is successful.
static bool ParseHead(const StringRef &Input, StringRef &FName,
uint64_t &NumSamples, uint64_t &NumHeadSamples) {
if (Input[0] == ' ')
return false;
size_t n2 = Input.rfind(':');
size_t n1 = Input.rfind(':', n2 - 1);
FName = Input.substr(0, n1);
if (Input.substr(n1 + 1, n2 - n1 - 1).getAsInteger(10, NumSamples))
return false;
if (Input.substr(n2 + 1).getAsInteger(10, NumHeadSamples))
return false;
return true;
}
/// Returns true if line offset \p L is legal (only has 16 bits).
static bool isOffsetLegal(unsigned L) { return (L & 0xffff) == L; }
/// Parse \p Input that contains metadata.
/// Possible metadata:
/// - CFG Checksum information:
/// !CFGChecksum: 12345
/// - CFG Checksum information:
/// !Attributes: 1
/// Stores the FunctionHash (a.k.a. CFG Checksum) into \p FunctionHash.
static bool parseMetadata(const StringRef &Input, uint64_t &FunctionHash,
uint32_t &Attributes) {
if (Input.startswith("!CFGChecksum:")) {
StringRef CFGInfo = Input.substr(strlen("!CFGChecksum:")).trim();
return !CFGInfo.getAsInteger(10, FunctionHash);
}
if (Input.startswith("!Attributes:")) {
StringRef Attrib = Input.substr(strlen("!Attributes:")).trim();
return !Attrib.getAsInteger(10, Attributes);
}
return false;
}
enum class LineType {
CallSiteProfile,
BodyProfile,
Metadata,
};
/// Parse \p Input as line sample.
///
/// \param Input input line.
/// \param LineTy Type of this line.
/// \param Depth the depth of the inline stack.
/// \param NumSamples total samples of the line/inlined callsite.
/// \param LineOffset line offset to the start of the function.
/// \param Discriminator discriminator of the line.
/// \param TargetCountMap map from indirect call target to count.
/// \param FunctionHash the function's CFG hash, used by pseudo probe.
///
/// returns true if parsing is successful.
static bool ParseLine(const StringRef &Input, LineType &LineTy, uint32_t &Depth,
uint64_t &NumSamples, uint32_t &LineOffset,
uint32_t &Discriminator, StringRef &CalleeName,
DenseMap<StringRef, uint64_t> &TargetCountMap,
uint64_t &FunctionHash, uint32_t &Attributes) {
for (Depth = 0; Input[Depth] == ' '; Depth++)
;
if (Depth == 0)
return false;
if (Input[Depth] == '!') {
LineTy = LineType::Metadata;
return parseMetadata(Input.substr(Depth), FunctionHash, Attributes);
}
size_t n1 = Input.find(':');
StringRef Loc = Input.substr(Depth, n1 - Depth);
size_t n2 = Loc.find('.');
if (n2 == StringRef::npos) {
if (Loc.getAsInteger(10, LineOffset) || !isOffsetLegal(LineOffset))
return false;
Discriminator = 0;
} else {
if (Loc.substr(0, n2).getAsInteger(10, LineOffset))
return false;
if (Loc.substr(n2 + 1).getAsInteger(10, Discriminator))
return false;
}
StringRef Rest = Input.substr(n1 + 2);
if (isDigit(Rest[0])) {
LineTy = LineType::BodyProfile;
size_t n3 = Rest.find(' ');
if (n3 == StringRef::npos) {
if (Rest.getAsInteger(10, NumSamples))
return false;
} else {
if (Rest.substr(0, n3).getAsInteger(10, NumSamples))
return false;
}
// Find call targets and their sample counts.
// Note: In some cases, there are symbols in the profile which are not
// mangled. To accommodate such cases, use colon + integer pairs as the
// anchor points.
// An example:
// _M_construct<char *>:1000 string_view<std::allocator<char> >:437
// ":1000" and ":437" are used as anchor points so the string above will
// be interpreted as
// target: _M_construct<char *>
// count: 1000
// target: string_view<std::allocator<char> >
// count: 437
while (n3 != StringRef::npos) {
n3 += Rest.substr(n3).find_first_not_of(' ');
Rest = Rest.substr(n3);
n3 = Rest.find_first_of(':');
if (n3 == StringRef::npos || n3 == 0)
return false;
StringRef Target;
uint64_t count, n4;
while (true) {
// Get the segment after the current colon.
StringRef AfterColon = Rest.substr(n3 + 1);
// Get the target symbol before the current colon.
Target = Rest.substr(0, n3);
// Check if the word after the current colon is an integer.
n4 = AfterColon.find_first_of(' ');
n4 = (n4 != StringRef::npos) ? n3 + n4 + 1 : Rest.size();
StringRef WordAfterColon = Rest.substr(n3 + 1, n4 - n3 - 1);
if (!WordAfterColon.getAsInteger(10, count))
break;
// Try to find the next colon.
uint64_t n5 = AfterColon.find_first_of(':');
if (n5 == StringRef::npos)
return false;
n3 += n5 + 1;
}
// An anchor point is found. Save the {target, count} pair
TargetCountMap[Target] = count;
if (n4 == Rest.size())
break;
// Change n3 to the next blank space after colon + integer pair.
n3 = n4;
}
} else {
LineTy = LineType::CallSiteProfile;
size_t n3 = Rest.find_last_of(':');
CalleeName = Rest.substr(0, n3);
if (Rest.substr(n3 + 1).getAsInteger(10, NumSamples))
return false;
}
return true;
}
/// Load samples from a text file.
///
/// See the documentation at the top of the file for an explanation of
/// the expected format.
///
/// \returns true if the file was loaded successfully, false otherwise.
std::error_code SampleProfileReaderText::readImpl() {
line_iterator LineIt(*Buffer, /*SkipBlanks=*/true, '#');
sampleprof_error Result = sampleprof_error::success;
InlineCallStack InlineStack;
uint32_t TopLevelProbeProfileCount = 0;
// DepthMetadata tracks whether we have processed metadata for the current
// top-level or nested function profile.
uint32_t DepthMetadata = 0;
ProfileIsFS = ProfileIsFSDisciminator;
FunctionSamples::ProfileIsFS = ProfileIsFS;
for (; !LineIt.is_at_eof(); ++LineIt) {
if ((*LineIt)[(*LineIt).find_first_not_of(' ')] == '#')
continue;
// Read the header of each function.
//
// Note that for function identifiers we are actually expecting
// mangled names, but we may not always get them. This happens when
// the compiler decides not to emit the function (e.g., it was inlined
// and removed). In this case, the binary will not have the linkage
// name for the function, so the profiler will emit the function's
// unmangled name, which may contain characters like ':' and '>' in its
// name (member functions, templates, etc).
//
// The only requirement we place on the identifier, then, is that it
// should not begin with a number.
if ((*LineIt)[0] != ' ') {
uint64_t NumSamples, NumHeadSamples;
StringRef FName;
if (!ParseHead(*LineIt, FName, NumSamples, NumHeadSamples)) {
reportError(LineIt.line_number(),
"Expected 'mangled_name:NUM:NUM', found " + *LineIt);
return sampleprof_error::malformed;
}
DepthMetadata = 0;
SampleContext FContext(FName, CSNameTable);
if (FContext.hasContext())
++CSProfileCount;
Profiles[FContext] = FunctionSamples();
FunctionSamples &FProfile = Profiles[FContext];
FProfile.setContext(FContext);
MergeResult(Result, FProfile.addTotalSamples(NumSamples));
MergeResult(Result, FProfile.addHeadSamples(NumHeadSamples));
InlineStack.clear();
InlineStack.push_back(&FProfile);
} else {
uint64_t NumSamples;
StringRef FName;
DenseMap<StringRef, uint64_t> TargetCountMap;
uint32_t Depth, LineOffset, Discriminator;
LineType LineTy;
uint64_t FunctionHash = 0;
uint32_t Attributes = 0;
if (!ParseLine(*LineIt, LineTy, Depth, NumSamples, LineOffset,
Discriminator, FName, TargetCountMap, FunctionHash,
Attributes)) {
reportError(LineIt.line_number(),
"Expected 'NUM[.NUM]: NUM[ mangled_name:NUM]*', found " +
*LineIt);
return sampleprof_error::malformed;
}
if (LineTy != LineType::Metadata && Depth == DepthMetadata) {
// Metadata must be put at the end of a function profile.
reportError(LineIt.line_number(),
"Found non-metadata after metadata: " + *LineIt);
return sampleprof_error::malformed;
}
// Here we handle FS discriminators.
Discriminator &= getDiscriminatorMask();
while (InlineStack.size() > Depth) {
InlineStack.pop_back();
}
switch (LineTy) {
case LineType::CallSiteProfile: {
FunctionSamples &FSamples = InlineStack.back()->functionSamplesAt(
LineLocation(LineOffset, Discriminator))[std::string(FName)];
FSamples.setName(FName);
MergeResult(Result, FSamples.addTotalSamples(NumSamples));
InlineStack.push_back(&FSamples);
DepthMetadata = 0;
break;
}
case LineType::BodyProfile: {
while (InlineStack.size() > Depth) {
InlineStack.pop_back();
}
FunctionSamples &FProfile = *InlineStack.back();
for (const auto &name_count : TargetCountMap) {
MergeResult(Result, FProfile.addCalledTargetSamples(
LineOffset, Discriminator, name_count.first,
name_count.second));
}
MergeResult(Result, FProfile.addBodySamples(LineOffset, Discriminator,
NumSamples));
break;
}
case LineType::Metadata: {
FunctionSamples &FProfile = *InlineStack.back();
if (FunctionHash) {
FProfile.setFunctionHash(FunctionHash);
if (Depth == 1)
++TopLevelProbeProfileCount;
}
FProfile.getContext().setAllAttributes(Attributes);
if (Attributes & (uint32_t)ContextShouldBeInlined)
ProfileIsCSNested = true;
DepthMetadata = Depth;
break;
}
}
}
}
assert((CSProfileCount == 0 || CSProfileCount == Profiles.size()) &&
"Cannot have both context-sensitive and regular profile");
ProfileIsCSFlat = (CSProfileCount > 0);
assert((TopLevelProbeProfileCount == 0 ||
TopLevelProbeProfileCount == Profiles.size()) &&
"Cannot have both probe-based profiles and regular profiles");
ProfileIsProbeBased = (TopLevelProbeProfileCount > 0);
FunctionSamples::ProfileIsProbeBased = ProfileIsProbeBased;
FunctionSamples::ProfileIsCSFlat = ProfileIsCSFlat;
FunctionSamples::ProfileIsCSNested = ProfileIsCSNested;
if (Result == sampleprof_error::success)
computeSummary();
return Result;
}
bool SampleProfileReaderText::hasFormat(const MemoryBuffer &Buffer) {
bool result = false;
// Check that the first non-comment line is a valid function header.
line_iterator LineIt(Buffer, /*SkipBlanks=*/true, '#');
if (!LineIt.is_at_eof()) {
if ((*LineIt)[0] != ' ') {
uint64_t NumSamples, NumHeadSamples;
StringRef FName;
result = ParseHead(*LineIt, FName, NumSamples, NumHeadSamples);
}
}
return result;
}
template <typename T> ErrorOr<T> SampleProfileReaderBinary::readNumber() {
unsigned NumBytesRead = 0;
std::error_code EC;
uint64_t Val = decodeULEB128(Data, &NumBytesRead);
if (Val > std::numeric_limits<T>::max())
EC = sampleprof_error::malformed;
else if (Data + NumBytesRead > End)
EC = sampleprof_error::truncated;
else
EC = sampleprof_error::success;
if (EC) {
reportError(0, EC.message());
return EC;
}
Data += NumBytesRead;
return static_cast<T>(Val);
}
ErrorOr<StringRef> SampleProfileReaderBinary::readString() {
std::error_code EC;
StringRef Str(reinterpret_cast<const char *>(Data));
if (Data + Str.size() + 1 > End) {
EC = sampleprof_error::truncated;
reportError(0, EC.message());
return EC;
}
Data += Str.size() + 1;
return Str;
}
template <typename T>
ErrorOr<T> SampleProfileReaderBinary::readUnencodedNumber() {
std::error_code EC;
if (Data + sizeof(T) > End) {
EC = sampleprof_error::truncated;
reportError(0, EC.message());
return EC;
}
using namespace support;
T Val = endian::readNext<T, little, unaligned>(Data);
return Val;
}
template <typename T>
inline ErrorOr<uint32_t> SampleProfileReaderBinary::readStringIndex(T &Table) {
std::error_code EC;
auto Idx = readNumber<uint32_t>();
if (std::error_code EC = Idx.getError())
return EC;
if (*Idx >= Table.size())
return sampleprof_error::truncated_name_table;
return *Idx;
}
ErrorOr<StringRef> SampleProfileReaderBinary::readStringFromTable() {
auto Idx = readStringIndex(NameTable);
if (std::error_code EC = Idx.getError())
return EC;
return NameTable[*Idx];
}
ErrorOr<SampleContext> SampleProfileReaderBinary::readSampleContextFromTable() {
auto FName(readStringFromTable());
if (std::error_code EC = FName.getError())
return EC;
return SampleContext(*FName);
}
ErrorOr<StringRef> SampleProfileReaderExtBinaryBase::readStringFromTable() {
if (!FixedLengthMD5)
return SampleProfileReaderBinary::readStringFromTable();
// read NameTable index.
auto Idx = readStringIndex(NameTable);
if (std::error_code EC = Idx.getError())
return EC;
// Check whether the name to be accessed has been accessed before,
// if not, read it from memory directly.
StringRef &SR = NameTable[*Idx];
if (SR.empty()) {
const uint8_t *SavedData = Data;
Data = MD5NameMemStart + ((*Idx) * sizeof(uint64_t));
auto FID = readUnencodedNumber<uint64_t>();
if (std::error_code EC = FID.getError())
return EC;
// Save the string converted from uint64_t in MD5StringBuf. All the
// references to the name are all StringRefs refering to the string
// in MD5StringBuf.
MD5StringBuf->push_back(std::to_string(*FID));
SR = MD5StringBuf->back();
Data = SavedData;
}
return SR;
}
ErrorOr<StringRef> SampleProfileReaderCompactBinary::readStringFromTable() {
auto Idx = readStringIndex(NameTable);
if (std::error_code EC = Idx.getError())
return EC;
return StringRef(NameTable[*Idx]);
}
std::error_code
SampleProfileReaderBinary::readProfile(FunctionSamples &FProfile) {
auto NumSamples = readNumber<uint64_t>();
if (std::error_code EC = NumSamples.getError())
return EC;
FProfile.addTotalSamples(*NumSamples);
// Read the samples in the body.
auto NumRecords = readNumber<uint32_t>();
if (std::error_code EC = NumRecords.getError())
return EC;
for (uint32_t I = 0; I < *NumRecords; ++I) {
auto LineOffset = readNumber<uint64_t>();
if (std::error_code EC = LineOffset.getError())
return EC;
if (!isOffsetLegal(*LineOffset)) {
return std::error_code();
}
auto Discriminator = readNumber<uint64_t>();
if (std::error_code EC = Discriminator.getError())
return EC;
auto NumSamples = readNumber<uint64_t>();
if (std::error_code EC = NumSamples.getError())
return EC;
auto NumCalls = readNumber<uint32_t>();
if (std::error_code EC = NumCalls.getError())
return EC;
// Here we handle FS discriminators:
uint32_t DiscriminatorVal = (*Discriminator) & getDiscriminatorMask();
for (uint32_t J = 0; J < *NumCalls; ++J) {
auto CalledFunction(readStringFromTable());
if (std::error_code EC = CalledFunction.getError())
return EC;
auto CalledFunctionSamples = readNumber<uint64_t>();
if (std::error_code EC = CalledFunctionSamples.getError())
return EC;
FProfile.addCalledTargetSamples(*LineOffset, DiscriminatorVal,
*CalledFunction, *CalledFunctionSamples);
}
FProfile.addBodySamples(*LineOffset, DiscriminatorVal, *NumSamples);
}
// Read all the samples for inlined function calls.
auto NumCallsites = readNumber<uint32_t>();
if (std::error_code EC = NumCallsites.getError())
return EC;
for (uint32_t J = 0; J < *NumCallsites; ++J) {
auto LineOffset = readNumber<uint64_t>();
if (std::error_code EC = LineOffset.getError())
return EC;
auto Discriminator = readNumber<uint64_t>();
if (std::error_code EC = Discriminator.getError())
return EC;
auto FName(readStringFromTable());
if (std::error_code EC = FName.getError())
return EC;
// Here we handle FS discriminators:
uint32_t DiscriminatorVal = (*Discriminator) & getDiscriminatorMask();
FunctionSamples &CalleeProfile = FProfile.functionSamplesAt(
LineLocation(*LineOffset, DiscriminatorVal))[std::string(*FName)];
CalleeProfile.setName(*FName);
if (std::error_code EC = readProfile(CalleeProfile))
return EC;
}
return sampleprof_error::success;
}
std::error_code
SampleProfileReaderBinary::readFuncProfile(const uint8_t *Start) {
Data = Start;
auto NumHeadSamples = readNumber<uint64_t>();
if (std::error_code EC = NumHeadSamples.getError())
return EC;
ErrorOr<SampleContext> FContext(readSampleContextFromTable());
if (std::error_code EC = FContext.getError())
return EC;
Profiles[*FContext] = FunctionSamples();
FunctionSamples &FProfile = Profiles[*FContext];
FProfile.setContext(*FContext);
FProfile.addHeadSamples(*NumHeadSamples);
if (FContext->hasContext())
CSProfileCount++;
if (std::error_code EC = readProfile(FProfile))
return EC;
return sampleprof_error::success;
}
std::error_code SampleProfileReaderBinary::readImpl() {
ProfileIsFS = ProfileIsFSDisciminator;
FunctionSamples::ProfileIsFS = ProfileIsFS;
while (!at_eof()) {
if (std::error_code EC = readFuncProfile(Data))
return EC;
}
return sampleprof_error::success;
}
ErrorOr<SampleContextFrames>
SampleProfileReaderExtBinaryBase::readContextFromTable() {
auto ContextIdx = readNumber<uint32_t>();
if (std::error_code EC = ContextIdx.getError())
return EC;
if (*ContextIdx >= CSNameTable->size())
return sampleprof_error::truncated_name_table;
return (*CSNameTable)[*ContextIdx];
}
ErrorOr<SampleContext>
SampleProfileReaderExtBinaryBase::readSampleContextFromTable() {
if (ProfileIsCSFlat) {
auto FContext(readContextFromTable());
if (std::error_code EC = FContext.getError())
return EC;
return SampleContext(*FContext);
} else {
auto FName(readStringFromTable());
if (std::error_code EC = FName.getError())
return EC;
return SampleContext(*FName);
}
}
std::error_code SampleProfileReaderExtBinaryBase::readOneSection(
const uint8_t *Start, uint64_t Size, const SecHdrTableEntry &Entry) {
Data = Start;
End = Start + Size;
switch (Entry.Type) {
case SecProfSummary:
if (std::error_code EC = readSummary())
return EC;
if (hasSecFlag(Entry, SecProfSummaryFlags::SecFlagPartial))
Summary->setPartialProfile(true);
if (hasSecFlag(Entry, SecProfSummaryFlags::SecFlagFullContext))
FunctionSamples::ProfileIsCSFlat = ProfileIsCSFlat = true;
if (hasSecFlag(Entry, SecProfSummaryFlags::SecFlagIsCSNested))
FunctionSamples::ProfileIsCSNested = ProfileIsCSNested;
if (hasSecFlag(Entry, SecProfSummaryFlags::SecFlagFSDiscriminator))
FunctionSamples::ProfileIsFS = ProfileIsFS = true;
break;
case SecNameTable: {
FixedLengthMD5 =
hasSecFlag(Entry, SecNameTableFlags::SecFlagFixedLengthMD5);
bool UseMD5 = hasSecFlag(Entry, SecNameTableFlags::SecFlagMD5Name);
assert((!FixedLengthMD5 || UseMD5) &&
"If FixedLengthMD5 is true, UseMD5 has to be true");
FunctionSamples::HasUniqSuffix =
hasSecFlag(Entry, SecNameTableFlags::SecFlagUniqSuffix);
if (std::error_code EC = readNameTableSec(UseMD5))
return EC;
break;
}
case SecCSNameTable: {
if (std::error_code EC = readCSNameTableSec())
return EC;
break;
}
case SecLBRProfile:
if (std::error_code EC = readFuncProfiles())
return EC;
break;
case SecFuncOffsetTable:
FuncOffsetsOrdered = hasSecFlag(Entry, SecFuncOffsetFlags::SecFlagOrdered);
if (std::error_code EC = readFuncOffsetTable())
return EC;
break;
case SecFuncMetadata: {
ProfileIsProbeBased =
hasSecFlag(Entry, SecFuncMetadataFlags::SecFlagIsProbeBased);
FunctionSamples::ProfileIsProbeBased = ProfileIsProbeBased;
bool HasAttribute =
hasSecFlag(Entry, SecFuncMetadataFlags::SecFlagHasAttribute);
if (std::error_code EC = readFuncMetadata(HasAttribute))
return EC;
break;
}
case SecProfileSymbolList:
if (std::error_code EC = readProfileSymbolList())
return EC;
break;
default:
if (std::error_code EC = readCustomSection(Entry))
return EC;
break;
}
return sampleprof_error::success;
}
bool SampleProfileReaderExtBinaryBase::collectFuncsFromModule() {
if (!M)
return false;
FuncsToUse.clear();
for (auto &F : *M)
FuncsToUse.insert(FunctionSamples::getCanonicalFnName(F));
return true;
}
std::error_code SampleProfileReaderExtBinaryBase::readFuncOffsetTable() {
// If there are more than one FuncOffsetTable, the profile read associated
// with previous FuncOffsetTable has to be done before next FuncOffsetTable
// is read.
FuncOffsetTable.clear();
auto Size = readNumber<uint64_t>();
if (std::error_code EC = Size.getError())
return EC;
FuncOffsetTable.reserve(*Size);
if (FuncOffsetsOrdered) {
OrderedFuncOffsets =
std::make_unique<std::vector<std::pair<SampleContext, uint64_t>>>();
OrderedFuncOffsets->reserve(*Size);
}
for (uint32_t I = 0; I < *Size; ++I) {
auto FContext(readSampleContextFromTable());
if (std::error_code EC = FContext.getError())
return EC;
auto Offset = readNumber<uint64_t>();
if (std::error_code EC = Offset.getError())
return EC;
FuncOffsetTable[*FContext] = *Offset;
if (FuncOffsetsOrdered)
OrderedFuncOffsets->emplace_back(*FContext, *Offset);
}
return sampleprof_error::success;
}
std::error_code SampleProfileReaderExtBinaryBase::readFuncProfiles() {
// Collect functions used by current module if the Reader has been
// given a module.
// collectFuncsFromModule uses FunctionSamples::getCanonicalFnName
// which will query FunctionSamples::HasUniqSuffix, so it has to be
// called after FunctionSamples::HasUniqSuffix is set, i.e. after
// NameTable section is read.
bool LoadFuncsToBeUsed = collectFuncsFromModule();
// When LoadFuncsToBeUsed is false, load all the function profiles.
const uint8_t *Start = Data;
if (!LoadFuncsToBeUsed) {
while (Data < End) {
if (std::error_code EC = readFuncProfile(Data))
return EC;
}
assert(Data == End && "More data is read than expected");
} else {
// Load function profiles on demand.
if (Remapper) {
for (auto Name : FuncsToUse) {
Remapper->insert(Name);
}
}
if (ProfileIsCSFlat) {
DenseSet<uint64_t> FuncGuidsToUse;
if (useMD5()) {
for (auto Name : FuncsToUse)
FuncGuidsToUse.insert(Function::getGUID(Name));
}
// For each function in current module, load all context profiles for
// the function as well as their callee contexts which can help profile
// guided importing for ThinLTO. This can be achieved by walking
// through an ordered context container, where contexts are laid out
// as if they were walked in preorder of a context trie. While
// traversing the trie, a link to the highest common ancestor node is
// kept so that all of its decendants will be loaded.
assert(OrderedFuncOffsets.get() &&
"func offset table should always be sorted in CS profile");
const SampleContext *CommonContext = nullptr;
for (const auto &NameOffset : *OrderedFuncOffsets) {
const auto &FContext = NameOffset.first;
auto FName = FContext.getName();
// For function in the current module, keep its farthest ancestor
// context. This can be used to load itself and its child and
// sibling contexts.
if ((useMD5() && FuncGuidsToUse.count(std::stoull(FName.data()))) ||
(!useMD5() && (FuncsToUse.count(FName) ||
(Remapper && Remapper->exist(FName))))) {
if (!CommonContext || !CommonContext->IsPrefixOf(FContext))
CommonContext = &FContext;
}
if (CommonContext == &FContext ||
(CommonContext && CommonContext->IsPrefixOf(FContext))) {
// Load profile for the current context which originated from
// the common ancestor.
const uint8_t *FuncProfileAddr = Start + NameOffset.second;
assert(FuncProfileAddr < End && "out of LBRProfile section");
if (std::error_code EC = readFuncProfile(FuncProfileAddr))
return EC;
}
}
} else {
if (useMD5()) {
for (auto Name : FuncsToUse) {
auto GUID = std::to_string(MD5Hash(Name));
auto iter = FuncOffsetTable.find(StringRef(GUID));
if (iter == FuncOffsetTable.end())
continue;
const uint8_t *FuncProfileAddr = Start + iter->second;
assert(FuncProfileAddr < End && "out of LBRProfile section");
if (std::error_code EC = readFuncProfile(FuncProfileAddr))
return EC;
}
} else {
for (auto NameOffset : FuncOffsetTable) {
SampleContext FContext(NameOffset.first);
auto FuncName = FContext.getName();
if (!FuncsToUse.count(FuncName) &&
(!Remapper || !Remapper->exist(FuncName)))
continue;
const uint8_t *FuncProfileAddr = Start + NameOffset.second;
assert(FuncProfileAddr < End && "out of LBRProfile section");
if (std::error_code EC = readFuncProfile(FuncProfileAddr))
return EC;
}
}
}
Data = End;
}
assert((CSProfileCount == 0 || CSProfileCount == Profiles.size()) &&
"Cannot have both context-sensitive and regular profile");
assert((!CSProfileCount || ProfileIsCSFlat) &&
"Section flag should be consistent with actual profile");
return sampleprof_error::success;
}
std::error_code SampleProfileReaderExtBinaryBase::readProfileSymbolList() {
if (!ProfSymList)
ProfSymList = std::make_unique<ProfileSymbolList>();
if (std::error_code EC = ProfSymList->read(Data, End - Data))
return EC;
Data = End;
return sampleprof_error::success;
}
std::error_code SampleProfileReaderExtBinaryBase::decompressSection(
const uint8_t *SecStart, const uint64_t SecSize,
const uint8_t *&DecompressBuf, uint64_t &DecompressBufSize) {
Data = SecStart;
End = SecStart + SecSize;
auto DecompressSize = readNumber<uint64_t>();
if (std::error_code EC = DecompressSize.getError())
return EC;
DecompressBufSize = *DecompressSize;
auto CompressSize = readNumber<uint64_t>();
if (std::error_code EC = CompressSize.getError())
return EC;
if (!llvm::zlib::isAvailable())
return sampleprof_error::zlib_unavailable;
StringRef CompressedStrings(reinterpret_cast<const char *>(Data),
*CompressSize);
char *Buffer = Allocator.Allocate<char>(DecompressBufSize);
size_t UCSize = DecompressBufSize;
llvm::Error E =
zlib::uncompress(CompressedStrings, Buffer, UCSize);
if (E)
return sampleprof_error::uncompress_failed;
DecompressBuf = reinterpret_cast<const uint8_t *>(Buffer);
return sampleprof_error::success;
}
std::error_code SampleProfileReaderExtBinaryBase::readImpl() {
const uint8_t *BufStart =
reinterpret_cast<const uint8_t *>(Buffer->getBufferStart());
for (auto &Entry : SecHdrTable) {
// Skip empty section.
if (!Entry.Size)
continue;
// Skip sections without context when SkipFlatProf is true.
if (SkipFlatProf && hasSecFlag(Entry, SecCommonFlags::SecFlagFlat))
continue;
const uint8_t *SecStart = BufStart + Entry.Offset;
uint64_t SecSize = Entry.Size;
// If the section is compressed, decompress it into a buffer
// DecompressBuf before reading the actual data. The pointee of
// 'Data' will be changed to buffer hold by DecompressBuf
// temporarily when reading the actual data.
bool isCompressed = hasSecFlag(Entry, SecCommonFlags::SecFlagCompress);
if (isCompressed) {
const uint8_t *DecompressBuf;
uint64_t DecompressBufSize;
if (std::error_code EC = decompressSection(
SecStart, SecSize, DecompressBuf, DecompressBufSize))
return EC;
SecStart = DecompressBuf;
SecSize = DecompressBufSize;
}
if (std::error_code EC = readOneSection(SecStart, SecSize, Entry))
return EC;
if (Data != SecStart + SecSize)
return sampleprof_error::malformed;
// Change the pointee of 'Data' from DecompressBuf to original Buffer.
if (isCompressed) {
Data = BufStart + Entry.Offset;
End = BufStart + Buffer->getBufferSize();
}
}
return sampleprof_error::success;
}
std::error_code SampleProfileReaderCompactBinary::readImpl() {
// Collect functions used by current module if the Reader has been
// given a module.
bool LoadFuncsToBeUsed = collectFuncsFromModule();
ProfileIsFS = ProfileIsFSDisciminator;
FunctionSamples::ProfileIsFS = ProfileIsFS;
std::vector<uint64_t> OffsetsToUse;
if (!LoadFuncsToBeUsed) {
// load all the function profiles.
for (auto FuncEntry : FuncOffsetTable) {
OffsetsToUse.push_back(FuncEntry.second);
}
} else {
// load function profiles on demand.
for (auto Name : FuncsToUse) {
auto GUID = std::to_string(MD5Hash(Name));
auto iter = FuncOffsetTable.find(StringRef(GUID));
if (iter == FuncOffsetTable.end())
continue;
OffsetsToUse.push_back(iter->second);
}
}
for (auto Offset : OffsetsToUse) {
const uint8_t *SavedData = Data;
if (std::error_code EC = readFuncProfile(
reinterpret_cast<const uint8_t *>(Buffer->getBufferStart()) +
Offset))
return EC;
Data = SavedData;
}
return sampleprof_error::success;
}
std::error_code SampleProfileReaderRawBinary::verifySPMagic(uint64_t Magic) {
if (Magic == SPMagic())
return sampleprof_error::success;
return sampleprof_error::bad_magic;
}
std::error_code SampleProfileReaderExtBinary::verifySPMagic(uint64_t Magic) {
if (Magic == SPMagic(SPF_Ext_Binary))
return sampleprof_error::success;
return sampleprof_error::bad_magic;
}
std::error_code
SampleProfileReaderCompactBinary::verifySPMagic(uint64_t Magic) {
if (Magic == SPMagic(SPF_Compact_Binary))
return sampleprof_error::success;
return sampleprof_error::bad_magic;
}
std::error_code SampleProfileReaderBinary::readNameTable() {
auto Size = readNumber<uint32_t>();
if (std::error_code EC = Size.getError())
return EC;
NameTable.reserve(*Size + NameTable.size());
for (uint32_t I = 0; I < *Size; ++I) {
auto Name(readString());