llvm-project/llvm/tools/llvm-cxxfilt/llvm-cxxfilt.cpp
Chandler Carruth dd647e3e60
Rework the Option library to reduce dynamic relocations (#119198)
Apologies for the large change, I looked for ways to break this up and
all of the ones I saw added real complexity. This change focuses on the
option's prefixed names and the array of prefixes. These are present in
every option and the dominant source of dynamic relocations for PIE or
PIC users of LLVM and Clang tooling. In some cases, 100s or 1000s of
them for the Clang driver which has a huge number of options.

This PR addresses this by building a string table and a prefixes table
that can be referenced with indices rather than pointers that require
dynamic relocations. This removes almost 7k dynmaic relocations from the
`clang` binary, roughly 8% of the remaining dynmaic relocations outside
of vtables. For busy-boxing use cases where many different option tables
are linked into the same binary, the savings add up a bit more.

The string table is a straightforward mechanism, but the prefixes
required some subtlety. They are encoded in a Pascal-string fashion with
a size followed by a sequence of offsets. This works relatively well for
the small realistic prefixes arrays in use.

Lots of code has to change in order to land this though: both all the
option library code has to be updated to use the string table and
prefixes table, and all the users of the options library have to be
updated to correctly instantiate the objects.

Some follow-up patches in the works to provide an abstraction for this
style of code, and to start using the same technique for some of the
other strings here now that the infrastructure is in place.
2024-12-11 15:44:44 -08:00

200 lines
6.3 KiB
C++

//===-- llvm-c++filt.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 "llvm/ADT/StringExtras.h"
#include "llvm/Demangle/Demangle.h"
#include "llvm/Demangle/StringViewExtras.h"
#include "llvm/Option/Arg.h"
#include "llvm/Option/ArgList.h"
#include "llvm/Option/Option.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/LLVMDriver.h"
#include "llvm/Support/WithColor.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/TargetParser/Host.h"
#include "llvm/TargetParser/Triple.h"
#include <cstdlib>
#include <iostream>
using namespace llvm;
namespace {
enum ID {
OPT_INVALID = 0, // This is not an option ID.
#define OPTION(...) LLVM_MAKE_OPT_ID(__VA_ARGS__),
#include "Opts.inc"
#undef OPTION
};
#define OPTTABLE_STR_TABLE_CODE
#include "Opts.inc"
#undef OPTTABLE_STR_TABLE_CODE
#define OPTTABLE_PREFIXES_TABLE_CODE
#include "Opts.inc"
#undef OPTTABLE_PREFIXES_TABLE_CODE
using namespace llvm::opt;
static constexpr opt::OptTable::Info InfoTable[] = {
#define OPTION(...) LLVM_CONSTRUCT_OPT_INFO(__VA_ARGS__),
#include "Opts.inc"
#undef OPTION
};
class CxxfiltOptTable : public opt::GenericOptTable {
public:
CxxfiltOptTable()
: opt::GenericOptTable(OptionStrTable, OptionPrefixesTable, InfoTable) {
setGroupedShortOptions(true);
}
};
} // namespace
static bool ParseParams;
static bool Quote;
static bool StripUnderscore;
static bool Types;
static StringRef ToolName;
static void error(const Twine &Message) {
WithColor::error(errs(), ToolName) << Message << '\n';
exit(1);
}
// Quote Undecorated with "" if asked for and not already followed by a '"'.
static std::string optionalQuote(const std::string &Undecorated,
StringRef Delimiters) {
if (Quote && (Delimiters.empty() || Delimiters[0] != '"'))
return '"' + Undecorated + '"';
return Undecorated;
}
static std::string demangle(const std::string &Mangled, StringRef Delimiters) {
using llvm::itanium_demangle::starts_with;
std::string_view DecoratedStr = Mangled;
bool CanHaveLeadingDot = true;
if (StripUnderscore && DecoratedStr[0] == '_') {
DecoratedStr.remove_prefix(1);
CanHaveLeadingDot = false;
}
std::string Result;
if (nonMicrosoftDemangle(DecoratedStr, Result, CanHaveLeadingDot,
ParseParams))
return optionalQuote(Result, Delimiters);
std::string Prefix;
char *Undecorated = nullptr;
if (Types)
Undecorated = itaniumDemangle(DecoratedStr, ParseParams);
if (!Undecorated && starts_with(DecoratedStr, "__imp_")) {
Prefix = "import thunk for ";
Undecorated = itaniumDemangle(DecoratedStr.substr(6), ParseParams);
}
Result =
Undecorated ? optionalQuote(Prefix + Undecorated, Delimiters) : Mangled;
free(Undecorated);
return Result;
}
// Split 'Source' on any character that fails to pass 'IsLegalChar'. The
// returned vector consists of pairs where 'first' is the delimited word, and
// 'second' are the delimiters following that word.
static void SplitStringDelims(
StringRef Source,
SmallVectorImpl<std::pair<StringRef, StringRef>> &OutFragments,
function_ref<bool(char)> IsLegalChar) {
// The beginning of the input string.
const auto Head = Source.begin();
// Obtain any leading delimiters.
auto Start = std::find_if(Head, Source.end(), IsLegalChar);
if (Start != Head)
OutFragments.push_back({"", Source.slice(0, Start - Head)});
// Capture each word and the delimiters following that word.
while (Start != Source.end()) {
Start = std::find_if(Start, Source.end(), IsLegalChar);
auto End = std::find_if_not(Start, Source.end(), IsLegalChar);
auto DEnd = std::find_if(End, Source.end(), IsLegalChar);
OutFragments.push_back({Source.slice(Start - Head, End - Head),
Source.slice(End - Head, DEnd - Head)});
Start = DEnd;
}
}
// This returns true if 'C' is a character that can show up in an
// Itanium-mangled string.
static bool IsLegalItaniumChar(char C) {
// Itanium CXX ABI [External Names]p5.1.1:
// '$' and '.' in mangled names are reserved for private implementations.
return isAlnum(C) || C == '.' || C == '$' || C == '_';
}
// If 'Split' is true, then 'Mangled' is broken into individual words and each
// word is demangled. Otherwise, the entire string is treated as a single
// mangled item. The result is output to 'OS'.
static void demangleLine(llvm::raw_ostream &OS, StringRef Mangled, bool Split) {
std::string Result;
if (Split) {
SmallVector<std::pair<StringRef, StringRef>, 16> Words;
SplitStringDelims(Mangled, Words, IsLegalItaniumChar);
for (const auto &Word : Words)
Result +=
::demangle(std::string(Word.first), Word.second) + Word.second.str();
} else
Result = ::demangle(std::string(Mangled), "");
OS << Result << '\n';
OS.flush();
}
int llvm_cxxfilt_main(int argc, char **argv, const llvm::ToolContext &) {
BumpPtrAllocator A;
StringSaver Saver(A);
CxxfiltOptTable Tbl;
ToolName = argv[0];
opt::InputArgList Args = Tbl.parseArgs(argc, argv, OPT_UNKNOWN, Saver,
[&](StringRef Msg) { error(Msg); });
if (Args.hasArg(OPT_help)) {
Tbl.printHelp(outs(),
(Twine(ToolName) + " [options] <mangled>").str().c_str(),
"LLVM symbol undecoration tool");
// TODO Replace this with OptTable API once it adds extrahelp support.
outs() << "\nPass @FILE as argument to read options from FILE.\n";
return 0;
}
if (Args.hasArg(OPT_version)) {
outs() << ToolName << '\n';
cl::PrintVersionMessage();
return 0;
}
StripUnderscore =
Args.hasFlag(OPT_strip_underscore, OPT_no_strip_underscore, false);
ParseParams = !Args.hasArg(OPT_no_params);
Quote = Args.hasArg(OPT_quote);
Types = Args.hasArg(OPT_types);
std::vector<std::string> Decorated = Args.getAllArgValues(OPT_INPUT);
if (Decorated.empty())
for (std::string Mangled; std::getline(std::cin, Mangled);)
demangleLine(llvm::outs(), Mangled, true);
else
for (const auto &Symbol : Decorated)
demangleLine(llvm::outs(), Symbol, false);
return EXIT_SUCCESS;
}