Files
clang-p2996/lld/MachO/MapFile.cpp
Roger Kim f84023a812 [lld][macho] Stop grouping symbols by sections in mapfile.
As per [Bug 50689](https://bugs.llvm.org/show_bug.cgi?id=50689),

```
2. getSectionSyms() puts all the symbols into a map of section -> symbols, but this seems unnecessary. This was likely copied from the ELF port, which prints a section header before the list of symbols it contains. But the Mach-O map file doesn't print these headers.
```

This diff removes `getSectionSyms()` and keeps all symbols in a flat vector.

What does ld64's mapfile look like?
```
$ llvm-mc -filetype=obj -triple=x86_64-apple-darwin test.s -o test.o
$ llvm-mc -filetype=obj -triple=x86_64-apple-darwin foo.s -o foo.o
$ ld -map map test.o foo.o -o out -L/Library/Developer/CommandLineTools/SDKs/MacOSX.sdk/usr/lib -lSystem
```

```
[  0] linker synthesized
[  1] test.o
[  2] foo.o
0x100003FB7     0x00000001      __TEXT  __text
0x100003FB8     0x00000000      __TEXT  obj
0x100003FB8     0x00000048      __TEXT  __unwind_info
0x100004000     0x00000001      __DATA  __common
0x100003FB7     0x00000001      [  1] _main
0x100003FB8     0x00000000      [  2] _foo
0x100003FB8     0x00000048      [  0] compact unwind info
0x100004000     0x00000001      [  1] _number
```

Perf numbers when linking chromium framework on a 16-Core Intel Xeon W Mac Pro:
```
base           diff           difference (95% CI)
sys_time   1.406 ± 0.020  1.388 ± 0.019  [  -1.9% ..   -0.6%]
user_time  5.557 ± 0.023  5.914 ± 0.020  [  +6.2% ..   +6.6%]
wall_time  4.455 ± 0.041  4.436 ± 0.035  [  -0.8% ..   -0.0%]
samples    35             35
```

Reviewed By: #lld-macho, int3

Differential Revision: https://reviews.llvm.org/D114735
2022-01-20 12:16:37 -08:00

137 lines
4.3 KiB
C++

//===- MapFile.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
//
//===----------------------------------------------------------------------===//
//
// This file implements the -map option. It shows lists in order and
// hierarchically the outputFile, arch, input files, output sections and
// symbol:
//
// # Path: test
// # Arch: x86_84
// # Object files:
// [ 0] linker synthesized
// [ 1] a.o
// # Sections:
// # Address Size Segment Section
// 0x1000005C0 0x0000004C __TEXT __text
// # Symbols:
// # Address File Name
// 0x1000005C0 [ 1] _main
//
//===----------------------------------------------------------------------===//
#include "MapFile.h"
#include "Config.h"
#include "InputFiles.h"
#include "InputSection.h"
#include "OutputSection.h"
#include "OutputSegment.h"
#include "Symbols.h"
#include "Target.h"
#include "llvm/Support/Parallel.h"
#include "llvm/Support/TimeProfiler.h"
using namespace llvm;
using namespace llvm::sys;
using namespace lld;
using namespace lld::macho;
// Returns a list of all symbols that we want to print out.
static std::vector<Defined *> getSymbols() {
std::vector<Defined *> v;
for (InputFile *file : inputFiles)
if (isa<ObjFile>(file))
for (Symbol *sym : file->symbols)
if (auto *d = dyn_cast_or_null<Defined>(sym))
if (d->isLive() && d->isec && d->getFile() == file) {
assert(!shouldOmitFromOutput(d->isec));
v.push_back(d);
}
return v;
}
// Construct a map from symbols to their stringified representations.
// Demangling symbols (which is what toString() does) is slow, so
// we do that in batch using parallel-for.
static DenseMap<Symbol *, std::string>
getSymbolStrings(ArrayRef<Defined *> syms) {
std::vector<std::string> str(syms.size());
parallelForEachN(0, syms.size(), [&](size_t i) {
raw_string_ostream os(str[i]);
os << toString(*syms[i]);
});
DenseMap<Symbol *, std::string> ret;
for (size_t i = 0, e = syms.size(); i < e; ++i)
ret[syms[i]] = std::move(str[i]);
return ret;
}
void macho::writeMapFile() {
if (config->mapFile.empty())
return;
TimeTraceScope timeScope("Write map file");
// Open a map file for writing.
std::error_code ec;
raw_fd_ostream os(config->mapFile, ec, sys::fs::OF_None);
if (ec) {
error("cannot open " + config->mapFile + ": " + ec.message());
return;
}
// Dump output path.
os << format("# Path: %s\n", config->outputFile.str().c_str());
// Dump output architecture.
os << format("# Arch: %s\n",
getArchitectureName(config->arch()).str().c_str());
// Dump table of object files.
os << "# Object files:\n";
os << format("[%3u] %s\n", 0, (const char *)"linker synthesized");
uint32_t fileIndex = 1;
DenseMap<lld::macho::InputFile *, uint32_t> readerToFileOrdinal;
for (InputFile *file : inputFiles) {
if (isa<ObjFile>(file)) {
os << format("[%3u] %s\n", fileIndex, file->getName().str().c_str());
readerToFileOrdinal[file] = fileIndex++;
}
}
// Collect symbol info that we want to print out.
std::vector<Defined *> syms = getSymbols();
parallelSort(syms.begin(), syms.end(), [](Defined *a, Defined *b) {
return a->getVA() != b->getVA() ? a->getVA() < b->getVA()
: a->getName() < b->getName();
});
DenseMap<Symbol *, std::string> symStr = getSymbolStrings(syms);
// Dump table of sections
os << "# Sections:\n";
os << "# Address\tSize \tSegment\tSection\n";
for (OutputSegment *seg : outputSegments)
for (OutputSection *osec : seg->getSections()) {
if (osec->isHidden())
continue;
os << format("0x%08llX\t0x%08llX\t%s\t%s\n", osec->addr, osec->getSize(),
seg->name.str().c_str(), osec->name.str().c_str());
}
// Dump table of symbols
os << "# Symbols:\n";
os << "# Address\t File Name\n";
for (Symbol *sym : syms) {
os << format("0x%08llX\t[%3u] %s\n", sym->getVA(),
readerToFileOrdinal[sym->getFile()], symStr[sym].c_str());
}
// TODO: when we implement -dead_strip, we should dump dead stripped symbols
}