Fix potential use-after-free bug#80
Merged
Rot127 merged 1 commit intocapstone-engine:auto-sync-18from May 16, 2025
Merged
Conversation
Sometimes there are corrupted characters in the generated files. It is due to the result of Regex::sub being a std::string, which is passed to the constructor of StringRef and then dropped prior to the use of the StringRef. This is a use-after-free bug, found by valgrind: ==566185== Invalid read of size 1 ==566185== at 0x6738C5: smatcher (regengine.inc:164) ==566185== by 0x6791E0: llvm_regexec (regexec.c:159) ==566185== by 0x5FAE8F: llvm::Regex::match(llvm::StringRef, llvm::SmallVectorImpl<llvm::StringRef>*, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >*) const (Regex.cpp:105) ==566185== by 0x4E6BE8: llvm::(anonymous namespace)::normalizedMnemonic(llvm::StringRef const&, bool, bool, llvm::StringRef) (PrinterCapstone.cpp:2683) ==566185== by 0x4E6E17: llvm::(anonymous namespace)::getNormalMnemonic(llvm::StringRef, llvm::StringRef, bool, bool) (PrinterCapstone.cpp:2700) ==566185== by 0x4ECBBE: llvm::(anonymous namespace)::printInsnNameMapEnumEntry(llvm::StringRef const&, std::unique_ptr<MatchableInfo, std::default_delete<MatchableInfo> > const&, llvm::raw_string_ostream&, llvm::raw_string_ostream&) (PrinterCapstone.cpp:3401) ==566185== by 0x4EF42B: llvm::PrinterCapstone::asmMatcherEmitMatchTable(llvm::CodeGenTarget const&, AsmMatcherInfo&, llvm::StringToOffsetTable&, unsigned int) const (PrinterCapstone.cpp:3676) ==566185== by 0x16F550: (anonymous namespace)::AsmMatcherEmitter::run() (AsmMatcherEmitter.cpp:2258) ==566185== by 0x16FB75: (anonymous namespace)::EmitAsmMatcher(llvm::RecordKeeper&, llvm::raw_ostream&) (AsmMatcherEmitter.cpp:2306) ==566185== by 0x6BEC3B: llvm::TableGenMain(char const*, std::function<bool (llvm::raw_ostream&, llvm::RecordKeeper&)>) (Main.cpp:136) ==566185== by 0x56F387: main (TableGen.cpp:84) ==566185== Address 0x951cf00 is 0 bytes inside a block of size 31 free'd ==566185== at 0x484499B: operator delete(void*, unsigned long) (vg_replace_malloc.c:935) ==566185== by 0x139604: std::__new_allocator<char>::deallocate(char*, unsigned long) (new_allocator.h:158) ==566185== by 0x138074: std::allocator_traits<std::allocator<char> >::deallocate(std::allocator<char>&, char*, unsigned long) (alloc_traits.h:496) ==566185== by 0x136777: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_destroy(unsigned long) (basic_string.h:292) ==566185== by 0x134F93: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_dispose() (basic_string.h:286) ==566185== by 0x133549: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::~basic_string() (basic_string.h:795) ==566185== by 0x4E6B85: llvm::(anonymous namespace)::normalizedMnemonic(llvm::StringRef const&, bool, bool, llvm::StringRef) (PrinterCapstone.cpp:2684) ==566185== by 0x4E6E17: llvm::(anonymous namespace)::getNormalMnemonic(llvm::StringRef, llvm::StringRef, bool, bool) (PrinterCapstone.cpp:2700) ==566185== by 0x4ECBBE: llvm::(anonymous namespace)::printInsnNameMapEnumEntry(llvm::StringRef const&, std::unique_ptr<MatchableInfo, std::default_delete<MatchableInfo> > const&, llvm::raw_string_ostream&, llvm::raw_string_ostream&) (PrinterCapstone.cpp:3401) ==566185== by 0x4EF42B: llvm::PrinterCapstone::asmMatcherEmitMatchTable(llvm::CodeGenTarget const&, AsmMatcherInfo&, llvm::StringToOffsetTable&, unsigned int) const (PrinterCapstone.cpp:3676) ==566185== by 0x16F550: (anonymous namespace)::AsmMatcherEmitter::run() (AsmMatcherEmitter.cpp:2258) ==566185== by 0x16FB75: (anonymous namespace)::EmitAsmMatcher(llvm::RecordKeeper&, llvm::raw_ostream&) (AsmMatcherEmitter.cpp:2306) ==566185== Block was alloc'd at ==566185== at 0x4841F2F: operator new(unsigned long) (vg_replace_malloc.c:422) ==566185== by 0x138958: std::__new_allocator<char>::allocate(unsigned long, void const*) (new_allocator.h:137) ==566185== by 0x13707F: std::allocator_traits<std::allocator<char> >::allocate(std::allocator<char>&, unsigned long) (alloc_traits.h:464) ==566185== by 0x1354B5: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_create(unsigned long&, unsigned long) (basic_string.tcc:155) ==566185== by 0x136F84: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_mutate(unsigned long, unsigned long, char const*, unsigned long) (basic_string.tcc:328) ==566185== by 0x1353D5: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_append(char const*, unsigned long) (basic_string.tcc:420) ==566185== by 0x1338FC: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::append(char const*, unsigned long) (basic_string.h:1422) ==566185== by 0x14EB57: llvm::operator+=(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&, llvm::StringRef) (StringRef.h:900) ==566185== by 0x5FB8C1: llvm::Regex::sub(llvm::StringRef, llvm::StringRef, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >*) const (Regex.cpp:224) ==566185== by 0x4E6B3D: llvm::(anonymous namespace)::normalizedMnemonic(llvm::StringRef const&, bool, bool, llvm::StringRef) (PrinterCapstone.cpp:2684) ==566185== by 0x4E6E17: llvm::(anonymous namespace)::getNormalMnemonic(llvm::StringRef, llvm::StringRef, bool, bool) (PrinterCapstone.cpp:2700) ==566185== by 0x4ECBBE: llvm::(anonymous namespace)::printInsnNameMapEnumEntry(llvm::StringRef const&, std::unique_ptr<MatchableInfo, std::default_delete<MatchableInfo> > const&, llvm::raw_string_ostream&, llvm::raw_string_ostream&) (PrinterCapstone.cpp:3401) To fix the bug, std::string is used instead of StringRef.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Sometimes there are corrupted characters in the generated files. It is due to the result of Regex::sub being a std::string, which is passed to the constructor of StringRef and then dropped prior to the use of the StringRef. This is a use-after-free bug, found by valgrind:
==566185== Invalid read of size 1
==566185== at 0x6738C5: smatcher (regengine.inc:164)
==566185== by 0x6791E0: llvm_regexec (regexec.c:159)
==566185== by 0x5FAE8F: llvm::Regex::match(llvm::StringRef, llvm::SmallVectorImplllvm::StringRef, std::__cxx11::basic_string<char, std::char_traits, std::allocator >) const (Regex.cpp:105)
==566185== by 0x4E6BE8: llvm::(anonymous namespace)::normalizedMnemonic(llvm::StringRef const&, bool, bool, llvm::StringRef) (PrinterCapstone.cpp:2683)
==566185== by 0x4E6E17: llvm::(anonymous namespace)::getNormalMnemonic(llvm::StringRef, llvm::StringRef, bool, bool) (PrinterCapstone.cpp:2700)
==566185== by 0x4ECBBE: llvm::(anonymous namespace)::printInsnNameMapEnumEntry(llvm::StringRef const&, std::unique_ptr<MatchableInfo, std::default_delete > const&, llvm::raw_string_ostream&, llvm::raw_string_ostream&) (PrinterCapstone.cpp:3401)
==566185== by 0x4EF42B: llvm::PrinterCapstone::asmMatcherEmitMatchTable(llvm::CodeGenTarget const&, AsmMatcherInfo&, llvm::StringToOffsetTable&, unsigned int) const (PrinterCapstone.cpp:3676)
==566185== by 0x16F550: (anonymous namespace)::AsmMatcherEmitter::run() (AsmMatcherEmitter.cpp:2258)
==566185== by 0x16FB75: (anonymous namespace)::EmitAsmMatcher(llvm::RecordKeeper&, llvm::raw_ostream&) (AsmMatcherEmitter.cpp:2306)
==566185== by 0x6BEC3B: llvm::TableGenMain(char const*, std::function<bool (llvm::raw_ostream&, llvm::RecordKeeper&)>) (Main.cpp:136)
==566185== by 0x56F387: main (TableGen.cpp:84)
==566185== Address 0x951cf00 is 0 bytes inside a block of size 31 free'd
==566185== at 0x484499B: operator delete(void*, unsigned long) (vg_replace_malloc.c:935)
==566185== by 0x139604: std::__new_allocator::deallocate(char*, unsigned long) (new_allocator.h:158)
==566185== by 0x138074: std::allocator_traits<std::allocator >::deallocate(std::allocator&, char*, unsigned long) (alloc_traits.h:496)
==566185== by 0x136777: std::__cxx11::basic_string<char, std::char_traits, std::allocator >::_M_destroy(unsigned long) (basic_string.h:292)
==566185== by 0x134F93: std::__cxx11::basic_string<char, std::char_traits, std::allocator >::_M_dispose() (basic_string.h:286)
==566185== by 0x133549: std::__cxx11::basic_string<char, std::char_traits, std::allocator >::~basic_string() (basic_string.h:795)
==566185== by 0x4E6B85: llvm::(anonymous namespace)::normalizedMnemonic(llvm::StringRef const&, bool, bool, llvm::StringRef) (PrinterCapstone.cpp:2684)
==566185== by 0x4E6E17: llvm::(anonymous namespace)::getNormalMnemonic(llvm::StringRef, llvm::StringRef, bool, bool) (PrinterCapstone.cpp:2700)
==566185== by 0x4ECBBE: llvm::(anonymous namespace)::printInsnNameMapEnumEntry(llvm::StringRef const&, std::unique_ptr<MatchableInfo, std::default_delete > const&, llvm::raw_string_ostream&, llvm::raw_string_ostream&) (PrinterCapstone.cpp:3401)
==566185== by 0x4EF42B: llvm::PrinterCapstone::asmMatcherEmitMatchTable(llvm::CodeGenTarget const&, AsmMatcherInfo&, llvm::StringToOffsetTable&, unsigned int) const (PrinterCapstone.cpp:3676)
==566185== by 0x16F550: (anonymous namespace)::AsmMatcherEmitter::run() (AsmMatcherEmitter.cpp:2258)
==566185== by 0x16FB75: (anonymous namespace)::EmitAsmMatcher(llvm::RecordKeeper&, llvm::raw_ostream&) (AsmMatcherEmitter.cpp:2306)
==566185== Block was alloc'd at
==566185== at 0x4841F2F: operator new(unsigned long) (vg_replace_malloc.c:422)
==566185== by 0x138958: std::__new_allocator::allocate(unsigned long, void const*) (new_allocator.h:137)
==566185== by 0x13707F: std::allocator_traits<std::allocator >::allocate(std::allocator&, unsigned long) (alloc_traits.h:464)
==566185== by 0x1354B5: std::__cxx11::basic_string<char, std::char_traits, std::allocator >::_M_create(unsigned long&, unsigned long) (basic_string.tcc:155)
==566185== by 0x136F84: std::__cxx11::basic_string<char, std::char_traits, std::allocator >::_M_mutate(unsigned long, unsigned long, char const*, unsigned long) (basic_string.tcc:328)
==566185== by 0x1353D5: std::__cxx11::basic_string<char, std::char_traits, std::allocator >::_M_append(char const*, unsigned long) (basic_string.tcc:420)
==566185== by 0x1338FC: std::__cxx11::basic_string<char, std::char_traits, std::allocator >::append(char const*, unsigned long) (basic_string.h:1422)
==566185== by 0x14EB57: llvm::operator+=(std::__cxx11::basic_string<char, std::char_traits, std::allocator >&, llvm::StringRef) (StringRef.h:900)
==566185== by 0x5FB8C1: llvm::Regex::sub(llvm::StringRef, llvm::StringRef, std::__cxx11::basic_string<char, std::char_traits, std::allocator >*) const (Regex.cpp:224)
==566185== by 0x4E6B3D: llvm::(anonymous namespace)::normalizedMnemonic(llvm::StringRef const&, bool, bool, llvm::StringRef) (PrinterCapstone.cpp:2684)
==566185== by 0x4E6E17: llvm::(anonymous namespace)::getNormalMnemonic(llvm::StringRef, llvm::StringRef, bool, bool) (PrinterCapstone.cpp:2700)
==566185== by 0x4ECBBE: llvm::(anonymous namespace)::printInsnNameMapEnumEntry(llvm::StringRef const&, std::unique_ptr<MatchableInfo, std::default_delete > const&, llvm::raw_string_ostream&, llvm::raw_string_ostream&) (PrinterCapstone.cpp:3401)
To fix the bug, std::string is used instead of StringRef.
With this pull request, the invalid memory accesses are gone.