mirror of
https://github.com/RPCSX/llvm.git
synced 2024-11-28 06:00:28 +00:00
c22ac1df07
Summary: it's often the case when the rules in the SpecialCaseList are of the form hel.o*bar. That gives us a chance to build trigram index to quickly discard 99% of inputs without running a full regex. A similar idea was used in Google Code Search as described in the blog post: https://swtch.com/~rsc/regexp/regexp4.html The check is defeated, if there's at least one regex more complicated than that. In this case, all inputs will go through the regex. That said, the real-world rules are often simple or can be simplied. That considerably speeds up compiling Chromium with CFI and UBSan. As measured on Chromium's content_message_generator.cc: before, CFI: 44 s after, CFI: 23 s after, CFI, no blacklist: 23 s (~1% slower, but 3 runs were unable to show the difference) after, regular compilation to bitcode: 23 s Reviewers: pcc Subscribers: mgorny, llvm-commits Differential Revision: https://reviews.llvm.org/D27188 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@288303 91177308-0d34-0410-b5e6-96231b3b80d8
173 lines
5.9 KiB
C++
173 lines
5.9 KiB
C++
//===-- SpecialCaseList.cpp - special case list for sanitizers ------------===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This is a utility class for instrumentation passes (like AddressSanitizer
|
|
// or ThreadSanitizer) to avoid instrumenting some functions or global
|
|
// variables, or to instrument some functions or global variables in a specific
|
|
// way, based on a user-supplied list.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "llvm/Support/SpecialCaseList.h"
|
|
#include "llvm/Support/TrigramIndex.h"
|
|
#include "llvm/ADT/SmallVector.h"
|
|
#include "llvm/ADT/StringExtras.h"
|
|
#include "llvm/ADT/StringSet.h"
|
|
#include "llvm/Support/MemoryBuffer.h"
|
|
#include "llvm/Support/Regex.h"
|
|
#include <string>
|
|
#include <system_error>
|
|
#include <utility>
|
|
|
|
namespace llvm {
|
|
|
|
/// Represents a set of regular expressions. Regular expressions which are
|
|
/// "literal" (i.e. no regex metacharacters) are stored in Strings, while all
|
|
/// others are represented as a single pipe-separated regex in RegEx. The
|
|
/// reason for doing so is efficiency; StringSet is much faster at matching
|
|
/// literal strings than Regex.
|
|
struct SpecialCaseList::Entry {
|
|
StringSet<> Strings;
|
|
TrigramIndex Trigrams;
|
|
std::unique_ptr<Regex> RegEx;
|
|
|
|
bool match(StringRef Query) const {
|
|
if (Strings.count(Query))
|
|
return true;
|
|
if (Trigrams.isDefinitelyOut(Query))
|
|
return false;
|
|
return RegEx && RegEx->match(Query);
|
|
}
|
|
};
|
|
|
|
SpecialCaseList::SpecialCaseList() : Entries(), Regexps(), IsCompiled(false) {}
|
|
|
|
std::unique_ptr<SpecialCaseList>
|
|
SpecialCaseList::create(const std::vector<std::string> &Paths,
|
|
std::string &Error) {
|
|
std::unique_ptr<SpecialCaseList> SCL(new SpecialCaseList());
|
|
for (const auto &Path : Paths) {
|
|
ErrorOr<std::unique_ptr<MemoryBuffer>> FileOrErr =
|
|
MemoryBuffer::getFile(Path);
|
|
if (std::error_code EC = FileOrErr.getError()) {
|
|
Error = (Twine("can't open file '") + Path + "': " + EC.message()).str();
|
|
return nullptr;
|
|
}
|
|
std::string ParseError;
|
|
if (!SCL->parse(FileOrErr.get().get(), ParseError)) {
|
|
Error = (Twine("error parsing file '") + Path + "': " + ParseError).str();
|
|
return nullptr;
|
|
}
|
|
}
|
|
SCL->compile();
|
|
return SCL;
|
|
}
|
|
|
|
std::unique_ptr<SpecialCaseList> SpecialCaseList::create(const MemoryBuffer *MB,
|
|
std::string &Error) {
|
|
std::unique_ptr<SpecialCaseList> SCL(new SpecialCaseList());
|
|
if (!SCL->parse(MB, Error))
|
|
return nullptr;
|
|
SCL->compile();
|
|
return SCL;
|
|
}
|
|
|
|
std::unique_ptr<SpecialCaseList>
|
|
SpecialCaseList::createOrDie(const std::vector<std::string> &Paths) {
|
|
std::string Error;
|
|
if (auto SCL = create(Paths, Error))
|
|
return SCL;
|
|
report_fatal_error(Error);
|
|
}
|
|
|
|
bool SpecialCaseList::parse(const MemoryBuffer *MB, std::string &Error) {
|
|
// Iterate through each line in the blacklist file.
|
|
SmallVector<StringRef, 16> Lines;
|
|
SplitString(MB->getBuffer(), Lines, "\n\r");
|
|
int LineNo = 1;
|
|
for (auto I = Lines.begin(), E = Lines.end(); I != E; ++I, ++LineNo) {
|
|
// Ignore empty lines and lines starting with "#"
|
|
if (I->empty() || I->startswith("#"))
|
|
continue;
|
|
// Get our prefix and unparsed regexp.
|
|
std::pair<StringRef, StringRef> SplitLine = I->split(":");
|
|
StringRef Prefix = SplitLine.first;
|
|
if (SplitLine.second.empty()) {
|
|
// Missing ':' in the line.
|
|
Error = (Twine("malformed line ") + Twine(LineNo) + ": '" +
|
|
SplitLine.first + "'").str();
|
|
return false;
|
|
}
|
|
|
|
std::pair<StringRef, StringRef> SplitRegexp = SplitLine.second.split("=");
|
|
std::string Regexp = SplitRegexp.first;
|
|
StringRef Category = SplitRegexp.second;
|
|
|
|
// See if we can store Regexp in Strings.
|
|
auto &Entry = Entries[Prefix][Category];
|
|
if (Regex::isLiteralERE(Regexp)) {
|
|
Entry.Strings.insert(Regexp);
|
|
continue;
|
|
}
|
|
Entry.Trigrams.insert(Regexp);
|
|
|
|
// Replace * with .*
|
|
for (size_t pos = 0; (pos = Regexp.find('*', pos)) != std::string::npos;
|
|
pos += strlen(".*")) {
|
|
Regexp.replace(pos, strlen("*"), ".*");
|
|
}
|
|
|
|
// Check that the regexp is valid.
|
|
Regex CheckRE(Regexp);
|
|
std::string REError;
|
|
if (!CheckRE.isValid(REError)) {
|
|
Error = (Twine("malformed regex in line ") + Twine(LineNo) + ": '" +
|
|
SplitLine.second + "': " + REError).str();
|
|
return false;
|
|
}
|
|
|
|
// Add this regexp into the proper group by its prefix.
|
|
if (!Regexps[Prefix][Category].empty())
|
|
Regexps[Prefix][Category] += "|";
|
|
Regexps[Prefix][Category] += "^" + Regexp + "$";
|
|
}
|
|
return true;
|
|
}
|
|
|
|
void SpecialCaseList::compile() {
|
|
assert(!IsCompiled && "compile() should only be called once");
|
|
// Iterate through each of the prefixes, and create Regexs for them.
|
|
for (StringMap<StringMap<std::string>>::const_iterator I = Regexps.begin(),
|
|
E = Regexps.end();
|
|
I != E; ++I) {
|
|
for (StringMap<std::string>::const_iterator II = I->second.begin(),
|
|
IE = I->second.end();
|
|
II != IE; ++II) {
|
|
Entries[I->getKey()][II->getKey()].RegEx.reset(new Regex(II->getValue()));
|
|
}
|
|
}
|
|
Regexps.clear();
|
|
IsCompiled = true;
|
|
}
|
|
|
|
SpecialCaseList::~SpecialCaseList() {}
|
|
|
|
bool SpecialCaseList::inSection(StringRef Section, StringRef Query,
|
|
StringRef Category) const {
|
|
assert(IsCompiled && "SpecialCaseList::compile() was not called!");
|
|
StringMap<StringMap<Entry> >::const_iterator I = Entries.find(Section);
|
|
if (I == Entries.end()) return false;
|
|
StringMap<Entry>::const_iterator II = I->second.find(Category);
|
|
if (II == I->second.end()) return false;
|
|
|
|
return II->getValue().match(Query);
|
|
}
|
|
|
|
} // namespace llvm
|