File: InputSection.cpp

package info (click to toggle)
llvm-toolchain-13 1%3A13.0.1-11
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 1,418,840 kB
  • sloc: cpp: 5,290,826; ansic: 996,570; asm: 544,593; python: 188,212; objc: 72,027; lisp: 30,291; f90: 25,395; sh: 24,898; javascript: 9,780; pascal: 9,398; perl: 7,484; ml: 5,432; awk: 3,523; makefile: 2,913; xml: 953; cs: 573; fortran: 539
file content (243 lines) | stat: -rw-r--r-- 8,056 bytes parent folder | download | duplicates (3)
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
//===- InputSection.cpp ---------------------------------------------------===//
//
// 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 "InputSection.h"
#include "ConcatOutputSection.h"
#include "Config.h"
#include "InputFiles.h"
#include "OutputSegment.h"
#include "Symbols.h"
#include "SyntheticSections.h"
#include "Target.h"
#include "UnwindInfoSection.h"
#include "Writer.h"
#include "lld/Common/Memory.h"
#include "llvm/Support/Endian.h"
#include "llvm/Support/xxhash.h"

using namespace llvm;
using namespace llvm::MachO;
using namespace llvm::support;
using namespace lld;
using namespace lld::macho;

std::vector<ConcatInputSection *> macho::inputSections;

uint64_t InputSection::getFileSize() const {
  return isZeroFill(getFlags()) ? 0 : getSize();
}

uint64_t InputSection::getVA(uint64_t off) const {
  return parent->addr + getOffset(off);
}

static uint64_t resolveSymbolVA(const Symbol *sym, uint8_t type) {
  const RelocAttrs &relocAttrs = target->getRelocAttrs(type);
  if (relocAttrs.hasAttr(RelocAttrBits::BRANCH))
    return sym->resolveBranchVA();
  if (relocAttrs.hasAttr(RelocAttrBits::GOT))
    return sym->resolveGotVA();
  if (relocAttrs.hasAttr(RelocAttrBits::TLV))
    return sym->resolveTlvVA();
  return sym->getVA();
}

// ICF needs to hash any section that might potentially be duplicated so
// that it can match on content rather than identity.
bool ConcatInputSection::isHashableForICF() const {
  switch (sectionType(getFlags())) {
  case S_REGULAR:
    return true;
  case S_CSTRING_LITERALS:
  case S_4BYTE_LITERALS:
  case S_8BYTE_LITERALS:
  case S_16BYTE_LITERALS:
  case S_LITERAL_POINTERS:
    llvm_unreachable("found unexpected literal type in ConcatInputSection");
  case S_ZEROFILL:
  case S_GB_ZEROFILL:
  case S_NON_LAZY_SYMBOL_POINTERS:
  case S_LAZY_SYMBOL_POINTERS:
  case S_SYMBOL_STUBS:
  case S_MOD_INIT_FUNC_POINTERS:
  case S_MOD_TERM_FUNC_POINTERS:
  case S_COALESCED:
  case S_INTERPOSING:
  case S_DTRACE_DOF:
  case S_LAZY_DYLIB_SYMBOL_POINTERS:
  case S_THREAD_LOCAL_REGULAR:
  case S_THREAD_LOCAL_ZEROFILL:
  case S_THREAD_LOCAL_VARIABLES:
  case S_THREAD_LOCAL_VARIABLE_POINTERS:
  case S_THREAD_LOCAL_INIT_FUNCTION_POINTERS:
    return false;
  default:
    llvm_unreachable("Section type");
  }
}

void ConcatInputSection::hashForICF() {
  assert(data.data()); // zeroFill section data has nullptr with non-zero size
  assert(icfEqClass[0] == 0); // don't overwrite a unique ID!
  // Turn-on the top bit to guarantee that valid hashes have no collisions
  // with the small-integer unique IDs for ICF-ineligible sections
  icfEqClass[0] = xxHash64(data) | (1ull << 63);
}

void ConcatInputSection::foldIdentical(ConcatInputSection *copy) {
  align = std::max(align, copy->align);
  copy->live = false;
  copy->wasCoalesced = true;
  numRefs += copy->numRefs;
  copy->numRefs = 0;
  copy->replacement = this;
}

void ConcatInputSection::writeTo(uint8_t *buf) {
  assert(!shouldOmitFromOutput());

  if (getFileSize() == 0)
    return;

  memcpy(buf, data.data(), data.size());

  for (size_t i = 0; i < relocs.size(); i++) {
    const Reloc &r = relocs[i];
    uint8_t *loc = buf + r.offset;
    uint64_t referentVA = 0;
    if (target->hasAttr(r.type, RelocAttrBits::SUBTRAHEND)) {
      const Symbol *fromSym = r.referent.get<Symbol *>();
      const Reloc &minuend = relocs[++i];
      uint64_t minuendVA;
      if (const Symbol *toSym = minuend.referent.dyn_cast<Symbol *>())
        minuendVA = toSym->getVA() + minuend.addend;
      else {
        auto *referentIsec = minuend.referent.get<InputSection *>();
        assert(!::shouldOmitFromOutput(referentIsec));
        minuendVA = referentIsec->getVA(minuend.addend);
      }
      referentVA = minuendVA - fromSym->getVA();
    } else if (auto *referentSym = r.referent.dyn_cast<Symbol *>()) {
      if (target->hasAttr(r.type, RelocAttrBits::LOAD) &&
          !referentSym->isInGot())
        target->relaxGotLoad(loc, r.type);
      referentVA = resolveSymbolVA(referentSym, r.type) + r.addend;

      if (isThreadLocalVariables(getFlags())) {
        // References from thread-local variable sections are treated as offsets
        // relative to the start of the thread-local data memory area, which
        // is initialized via copying all the TLV data sections (which are all
        // contiguous).
        if (isa<Defined>(referentSym))
          referentVA -= firstTLVDataSection->addr;
      }
    } else if (auto *referentIsec = r.referent.dyn_cast<InputSection *>()) {
      assert(!::shouldOmitFromOutput(referentIsec));
      referentVA = referentIsec->getVA(r.addend);
    }
    target->relocateOne(loc, r, referentVA, getVA() + r.offset);
  }
}

void CStringInputSection::splitIntoPieces() {
  size_t off = 0;
  StringRef s = toStringRef(data);
  while (!s.empty()) {
    size_t end = s.find(0);
    if (end == StringRef::npos)
      fatal(toString(this) + ": string is not null terminated");
    size_t size = end + 1;
    uint32_t hash = config->dedupLiterals ? xxHash64(s.substr(0, size)) : 0;
    pieces.emplace_back(off, hash);
    s = s.substr(size);
    off += size;
  }
}

StringPiece &CStringInputSection::getStringPiece(uint64_t off) {
  if (off >= data.size())
    fatal(toString(this) + ": offset is outside the section");

  auto it =
      partition_point(pieces, [=](StringPiece p) { return p.inSecOff <= off; });
  return it[-1];
}

const StringPiece &CStringInputSection::getStringPiece(uint64_t off) const {
  return const_cast<CStringInputSection *>(this)->getStringPiece(off);
}

uint64_t CStringInputSection::getOffset(uint64_t off) const {
  const StringPiece &piece = getStringPiece(off);
  uint64_t addend = off - piece.inSecOff;
  return piece.outSecOff + addend;
}

WordLiteralInputSection::WordLiteralInputSection(StringRef segname,
                                                 StringRef name,
                                                 InputFile *file,
                                                 ArrayRef<uint8_t> data,
                                                 uint32_t align, uint32_t flags)
    : InputSection(WordLiteralKind, segname, name, file, data, align, flags) {
  switch (sectionType(flags)) {
  case S_4BYTE_LITERALS:
    power2LiteralSize = 2;
    break;
  case S_8BYTE_LITERALS:
    power2LiteralSize = 3;
    break;
  case S_16BYTE_LITERALS:
    power2LiteralSize = 4;
    break;
  default:
    llvm_unreachable("invalid literal section type");
  }

  live.resize(data.size() >> power2LiteralSize, !config->deadStrip);
}

uint64_t WordLiteralInputSection::getOffset(uint64_t off) const {
  auto *osec = cast<WordLiteralSection>(parent);
  const uint8_t *buf = data.data();
  switch (sectionType(getFlags())) {
  case S_4BYTE_LITERALS:
    return osec->getLiteral4Offset(buf + off);
  case S_8BYTE_LITERALS:
    return osec->getLiteral8Offset(buf + off);
  case S_16BYTE_LITERALS:
    return osec->getLiteral16Offset(buf + off);
  default:
    llvm_unreachable("invalid literal section type");
  }
}

bool macho::isCodeSection(const InputSection *isec) {
  uint32_t type = sectionType(isec->getFlags());
  if (type != S_REGULAR && type != S_COALESCED)
    return false;

  uint32_t attr = isec->getFlags() & SECTION_ATTRIBUTES_USR;
  if (attr == S_ATTR_PURE_INSTRUCTIONS)
    return true;

  if (isec->getSegName() == segment_names::text)
    return StringSwitch<bool>(isec->getName())
        .Cases(section_names::textCoalNt, section_names::staticInit, true)
        .Default(false);

  return false;
}

bool macho::isCfStringSection(const InputSection *isec) {
  return isec->getName() == section_names::cfString &&
         isec->getSegName() == segment_names::data;
}

std::string lld::toString(const InputSection *isec) {
  return (toString(isec->getFile()) + ":(" + isec->getName() + ")").str();
}