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
| //===- DbiStreamBuilder.cpp - PDB Dbi Stream Creation -----------*- 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 "llvm/DebugInfo/PDB/Native/GSIStreamBuilder.h"
#include "llvm/ADT/DenseSet.h"
#include "llvm/DebugInfo/CodeView/RecordName.h"
#include "llvm/DebugInfo/CodeView/SymbolDeserializer.h"
#include "llvm/DebugInfo/CodeView/SymbolRecord.h"
#include "llvm/DebugInfo/CodeView/SymbolSerializer.h"
#include "llvm/DebugInfo/MSF/MSFBuilder.h"
#include "llvm/DebugInfo/MSF/MSFCommon.h"
#include "llvm/DebugInfo/MSF/MappedBlockStream.h"
#include "llvm/DebugInfo/PDB/Native/GlobalsStream.h"
#include "llvm/DebugInfo/PDB/Native/Hash.h"
#include "llvm/Support/BinaryItemStream.h"
#include "llvm/Support/BinaryStreamWriter.h"
#include "llvm/Support/xxhash.h"
#include <algorithm>
#include <vector>
using namespace llvm;
using namespace llvm::msf;
using namespace llvm::pdb;
using namespace llvm::codeview;
struct llvm::pdb::GSIHashStreamBuilder {
struct SymbolDenseMapInfo {
static inline CVSymbol getEmptyKey() {
static CVSymbol Empty;
return Empty;
}
static inline CVSymbol getTombstoneKey() {
static CVSymbol Tombstone(
DenseMapInfo<ArrayRef<uint8_t>>::getTombstoneKey());
return Tombstone;
}
static unsigned getHashValue(const CVSymbol &Val) {
return xxHash64(Val.RecordData);
}
static bool isEqual(const CVSymbol &LHS, const CVSymbol &RHS) {
return LHS.RecordData == RHS.RecordData;
}
};
std::vector<CVSymbol> Records;
uint32_t StreamIndex;
llvm::DenseSet<CVSymbol, SymbolDenseMapInfo> SymbolHashes;
std::vector<PSHashRecord> HashRecords;
std::array<support::ulittle32_t, (IPHR_HASH + 32) / 32> HashBitmap;
std::vector<support::ulittle32_t> HashBuckets;
uint32_t calculateSerializedLength() const;
uint32_t calculateRecordByteSize() const;
Error commit(BinaryStreamWriter &Writer);
void finalizeBuckets(uint32_t RecordZeroOffset);
template <typename T> void addSymbol(const T &Symbol, MSFBuilder &Msf) {
T Copy(Symbol);
addSymbol(SymbolSerializer::writeOneSymbol(Copy, Msf.getAllocator(),
CodeViewContainer::Pdb));
}
void addSymbol(const CVSymbol &Symbol) {
if (Symbol.kind() == S_UDT || Symbol.kind() == S_CONSTANT) {
auto Iter = SymbolHashes.insert(Symbol);
if (!Iter.second)
return;
}
Records.push_back(Symbol);
}
};
uint32_t GSIHashStreamBuilder::calculateSerializedLength() const {
uint32_t Size = sizeof(GSIHashHeader);
Size += HashRecords.size() * sizeof(PSHashRecord);
Size += HashBitmap.size() * sizeof(uint32_t);
Size += HashBuckets.size() * sizeof(uint32_t);
return Size;
}
uint32_t GSIHashStreamBuilder::calculateRecordByteSize() const {
uint32_t Size = 0;
for (const auto &Sym : Records)
Size += Sym.length();
return Size;
}
Error GSIHashStreamBuilder::commit(BinaryStreamWriter &Writer) {
GSIHashHeader Header;
Header.VerSignature = GSIHashHeader::HdrSignature;
Header.VerHdr = GSIHashHeader::HdrVersion;
Header.HrSize = HashRecords.size() * sizeof(PSHashRecord);
Header.NumBuckets = HashBitmap.size() * 4 + HashBuckets.size() * 4;
if (auto EC = Writer.writeObject(Header))
return EC;
if (auto EC = Writer.writeArray(makeArrayRef(HashRecords)))
return EC;
if (auto EC = Writer.writeArray(makeArrayRef(HashBitmap)))
return EC;
if (auto EC = Writer.writeArray(makeArrayRef(HashBuckets)))
return EC;
return Error::success();
}
static bool isAsciiString(StringRef S) {
return llvm::all_of(S, [](char C) { return unsigned(C) < 0x80; });
}
// See `caseInsensitiveComparePchPchCchCch` in gsi.cpp
static bool gsiRecordLess(StringRef S1, StringRef S2) {
size_t LS = S1.size();
size_t RS = S2.size();
// Shorter strings always compare less than longer strings.
if (LS != RS)
return LS < RS;
// If either string contains non ascii characters, memcmp them.
if (LLVM_UNLIKELY(!isAsciiString(S1) || !isAsciiString(S2)))
return memcmp(S1.data(), S2.data(), LS) < 0;
// Both strings are ascii, perform a case-insenstive comparison.
return S1.compare_lower(S2.data()) < 0;
}
void GSIHashStreamBuilder::finalizeBuckets(uint32_t RecordZeroOffset) {
std::array<std::vector<std::pair<StringRef, PSHashRecord>>, IPHR_HASH + 1>
TmpBuckets;
uint32_t SymOffset = RecordZeroOffset;
for (const CVSymbol &Sym : Records) {
PSHashRecord HR;
// Add one when writing symbol offsets to disk. See GSI1::fixSymRecs.
HR.Off = SymOffset + 1;
HR.CRef = 1; // Always use a refcount of 1.
// Hash the name to figure out which bucket this goes into.
StringRef Name = getSymbolName(Sym);
size_t BucketIdx = hashStringV1(Name) % IPHR_HASH;
TmpBuckets[BucketIdx].push_back(std::make_pair(Name, HR));
SymOffset += Sym.length();
}
// Compute the three tables: the hash records in bucket and chain order, the
// bucket presence bitmap, and the bucket chain start offsets.
HashRecords.reserve(Records.size());
for (ulittle32_t &Word : HashBitmap)
Word = 0;
for (size_t BucketIdx = 0; BucketIdx < IPHR_HASH + 1; ++BucketIdx) {
auto &Bucket = TmpBuckets[BucketIdx];
if (Bucket.empty())
continue;
HashBitmap[BucketIdx / 32] |= 1U << (BucketIdx % 32);
// Calculate what the offset of the first hash record in the chain would
// be if it were inflated to contain 32-bit pointers. On a 32-bit system,
// each record would be 12 bytes. See HROffsetCalc in gsi.h.
const int SizeOfHROffsetCalc = 12;
ulittle32_t ChainStartOff =
ulittle32_t(HashRecords.size() * SizeOfHROffsetCalc);
HashBuckets.push_back(ChainStartOff);
// Sort each bucket by memcmp of the symbol's name. It's important that
// we use the same sorting algorithm as is used by the reference
// implementation to ensure that the search for a record within a bucket
// can properly early-out when it detects the record won't be found. The
// algorithm used here corredsponds to the function
// caseInsensitiveComparePchPchCchCch in the reference implementation.
llvm::sort(Bucket, [](const std::pair<StringRef, PSHashRecord> &Left,
const std::pair<StringRef, PSHashRecord> &Right) {
return gsiRecordLess(Left.first, Right.first);
});
for (const auto &Entry : Bucket)
HashRecords.push_back(Entry.second);
}
}
GSIStreamBuilder::GSIStreamBuilder(msf::MSFBuilder &Msf)
: Msf(Msf), PSH(std::make_unique<GSIHashStreamBuilder>()),
GSH(std::make_unique<GSIHashStreamBuilder>()) {}
GSIStreamBuilder::~GSIStreamBuilder() {}
uint32_t GSIStreamBuilder::calculatePublicsHashStreamSize() const {
uint32_t Size = 0;
Size += sizeof(PublicsStreamHeader);
Size += PSH->calculateSerializedLength();
Size += PSH->Records.size() * sizeof(uint32_t); // AddrMap
// FIXME: Add thunk map and section offsets for incremental linking.
return Size;
}
uint32_t GSIStreamBuilder::calculateGlobalsHashStreamSize() const {
return GSH->calculateSerializedLength();
}
Error GSIStreamBuilder::finalizeMsfLayout() {
// First we write public symbol records, then we write global symbol records.
uint32_t PSHZero = 0;
uint32_t GSHZero = PSH->calculateRecordByteSize();
PSH->finalizeBuckets(PSHZero);
GSH->finalizeBuckets(GSHZero);
Expected<uint32_t> Idx = Msf.addStream(calculateGlobalsHashStreamSize());
if (!Idx)
return Idx.takeError();
GSH->StreamIndex = *Idx;
Idx = Msf.addStream(calculatePublicsHashStreamSize());
if (!Idx)
return Idx.takeError();
PSH->StreamIndex = *Idx;
uint32_t RecordBytes =
GSH->calculateRecordByteSize() + PSH->calculateRecordByteSize();
Idx = Msf.addStream(RecordBytes);
if (!Idx)
return Idx.takeError();
RecordStreamIdx = *Idx;
return Error::success();
}
static bool comparePubSymByAddrAndName(
const std::pair<const CVSymbol *, const PublicSym32 *> &LS,
const std::pair<const CVSymbol *, const PublicSym32 *> &RS) {
if (LS.second->Segment != RS.second->Segment)
return LS.second->Segment < RS.second->Segment;
if (LS.second->Offset != RS.second->Offset)
return LS.second->Offset < RS.second->Offset;
return LS.second->Name < RS.second->Name;
}
/// Compute the address map. The address map is an array of symbol offsets
/// sorted so that it can be binary searched by address.
static std::vector<ulittle32_t> computeAddrMap(ArrayRef<CVSymbol> Records) {
// Make a vector of pointers to the symbols so we can sort it by address.
// Also gather the symbol offsets while we're at it.
std::vector<PublicSym32> DeserializedPublics;
std::vector<std::pair<const CVSymbol *, const PublicSym32 *>> PublicsByAddr;
std::vector<uint32_t> SymOffsets;
DeserializedPublics.reserve(Records.size());
PublicsByAddr.reserve(Records.size());
SymOffsets.reserve(Records.size());
uint32_t SymOffset = 0;
for (const CVSymbol &Sym : Records) {
assert(Sym.kind() == SymbolKind::S_PUB32);
DeserializedPublics.push_back(
cantFail(SymbolDeserializer::deserializeAs<PublicSym32>(Sym)));
PublicsByAddr.emplace_back(&Sym, &DeserializedPublics.back());
SymOffsets.push_back(SymOffset);
SymOffset += Sym.length();
}
llvm::stable_sort(PublicsByAddr, comparePubSymByAddrAndName);
// Fill in the symbol offsets in the appropriate order.
std::vector<ulittle32_t> AddrMap;
AddrMap.reserve(Records.size());
for (auto &Sym : PublicsByAddr) {
ptrdiff_t Idx = std::distance(Records.data(), Sym.first);
assert(Idx >= 0 && size_t(Idx) < Records.size());
AddrMap.push_back(ulittle32_t(SymOffsets[Idx]));
}
return AddrMap;
}
uint32_t GSIStreamBuilder::getPublicsStreamIndex() const {
return PSH->StreamIndex;
}
uint32_t GSIStreamBuilder::getGlobalsStreamIndex() const {
return GSH->StreamIndex;
}
void GSIStreamBuilder::addPublicSymbol(const PublicSym32 &Pub) {
PSH->addSymbol(Pub, Msf);
}
void GSIStreamBuilder::addGlobalSymbol(const ProcRefSym &Sym) {
GSH->addSymbol(Sym, Msf);
}
void GSIStreamBuilder::addGlobalSymbol(const DataSym &Sym) {
GSH->addSymbol(Sym, Msf);
}
void GSIStreamBuilder::addGlobalSymbol(const ConstantSym &Sym) {
GSH->addSymbol(Sym, Msf);
}
void GSIStreamBuilder::addGlobalSymbol(const codeview::CVSymbol &Sym) {
GSH->addSymbol(Sym);
}
static Error writeRecords(BinaryStreamWriter &Writer,
ArrayRef<CVSymbol> Records) {
BinaryItemStream<CVSymbol> ItemStream(support::endianness::little);
ItemStream.setItems(Records);
BinaryStreamRef RecordsRef(ItemStream);
return Writer.writeStreamRef(RecordsRef);
}
Error GSIStreamBuilder::commitSymbolRecordStream(
WritableBinaryStreamRef Stream) {
BinaryStreamWriter Writer(Stream);
// Write public symbol records first, followed by global symbol records. This
// must match the order that we assume in finalizeMsfLayout when computing
// PSHZero and GSHZero.
if (auto EC = writeRecords(Writer, PSH->Records))
return EC;
if (auto EC = writeRecords(Writer, GSH->Records))
return EC;
return Error::success();
}
Error GSIStreamBuilder::commitPublicsHashStream(
WritableBinaryStreamRef Stream) {
BinaryStreamWriter Writer(Stream);
PublicsStreamHeader Header;
// FIXME: Fill these in. They are for incremental linking.
Header.SymHash = PSH->calculateSerializedLength();
Header.AddrMap = PSH->Records.size() * 4;
Header.NumThunks = 0;
Header.SizeOfThunk = 0;
Header.ISectThunkTable = 0;
memset(Header.Padding, 0, sizeof(Header.Padding));
Header.OffThunkTable = 0;
Header.NumSections = 0;
if (auto EC = Writer.writeObject(Header))
return EC;
if (auto EC = PSH->commit(Writer))
return EC;
std::vector<ulittle32_t> AddrMap = computeAddrMap(PSH->Records);
if (auto EC = Writer.writeArray(makeArrayRef(AddrMap)))
return EC;
return Error::success();
}
Error GSIStreamBuilder::commitGlobalsHashStream(
WritableBinaryStreamRef Stream) {
BinaryStreamWriter Writer(Stream);
return GSH->commit(Writer);
}
Error GSIStreamBuilder::commit(const msf::MSFLayout &Layout,
WritableBinaryStreamRef Buffer) {
auto GS = WritableMappedBlockStream::createIndexedStream(
Layout, Buffer, getGlobalsStreamIndex(), Msf.getAllocator());
auto PS = WritableMappedBlockStream::createIndexedStream(
Layout, Buffer, getPublicsStreamIndex(), Msf.getAllocator());
auto PRS = WritableMappedBlockStream::createIndexedStream(
Layout, Buffer, getRecordStreamIdx(), Msf.getAllocator());
if (auto EC = commitSymbolRecordStream(*PRS))
return EC;
if (auto EC = commitGlobalsHashStream(*GS))
return EC;
if (auto EC = commitPublicsHashStream(*PS))
return EC;
return Error::success();
}
|