Antoine Pitrou created ARROW-18031:
--------------------------------------

             Summary: [C++][Parquet] Undefined behavior in boolean RLE decoder
                 Key: ARROW-18031
                 URL: https://issues.apache.org/jira/browse/ARROW-18031
             Project: Apache Arrow
          Issue Type: Bug
          Components: C++, Parquet
            Reporter: Antoine Pitrou
             Fix For: 10.0.0


A fuzzing run found this undefined behavior, which hints that the RLE boolean 
decoder implementation is wrong:
{code}
#0  __GI_raise (sig=sig@entry=6) at ../sysdeps/unix/sysv/linux/raise.c:50
#1  0x00007ffff7a45859 in __GI_abort () at abort.c:79
#2  0x000055555beafa07 in __sanitizer::Abort() ()
#3  0x000055555bead8a1 in __sanitizer::Die() ()
#4  0x000055555bec15cc in __ubsan::ScopedReport::~ScopedReport() ()
#5  0x000055555bec437b in handleLoadInvalidValue(__ubsan::InvalidValueData*, 
unsigned long, __ubsan::ReportOptions) ()
#6  0x000055555bec43be in __ubsan_handle_load_invalid_value_abort ()
#7  0x000055555c5acb9b in arrow::bit_util::BitReader::GetAligned<bool> 
(this=0x607000001060, num_bytes=1, v=0x7fffffff99d0)
    at /home/antoine/arrow/dev/cpp/src/arrow/util/bit_stream_utils.h:415
#8  0x000055555c5aa7d4 in arrow::util::RleDecoder::NextCounts<bool> 
(this=0x607000001060) at 
/home/antoine/arrow/dev/cpp/src/arrow/util/rle_encoding.h:663
#9  0x000055555c5a7328 in arrow::util::RleDecoder::GetBatch<bool> 
(this=0x607000001060, values=0x7ffff5408000, batch_size=2089)
    at /home/antoine/arrow/dev/cpp/src/arrow/util/rle_encoding.h:329
#10 0x000055555c59834e in parquet::(anonymous 
namespace)::RleBooleanDecoder::Decode (this=0x606000003ce0, 
buffer=0x7ffff5408000, max_values=2089)
    at /home/antoine/arrow/dev/cpp/src/parquet/encoding.cc:2388
#11 0x000055555c4f43d9 in parquet::internal::(anonymous 
namespace)::TypedRecordReader<parquet::PhysicalType<(parquet::Type::type)0> 
>::ReadValuesDense (
    this=0x614000001050, values_to_read=2089) at 
/home/antoine/arrow/dev/cpp/src/parquet/column_reader.cc:1531
#12 0x000055555c4f7668 in parquet::internal::(anonymous 
namespace)::TypedRecordReader<parquet::PhysicalType<(parquet::Type::type)0> 
>::ReadRecordData (
    this=0x614000001050, num_records=2089) at 
/home/antoine/arrow/dev/cpp/src/parquet/column_reader.cc:1575
#13 0x000055555c4f03e5 in parquet::internal::(anonymous 
namespace)::TypedRecordReader<parquet::PhysicalType<(parquet::Type::type)0> 
>::ReadRecords (
    this=0x614000001050, num_records=2089) at 
/home/antoine/arrow/dev/cpp/src/parquet/column_reader.cc:1331
#14 0x000055555bf0acee in parquet::arrow::(anonymous 
namespace)::LeafReader::LoadBatch (this=0x608000001020, records_to_read=2089)
    at /home/antoine/arrow/dev/cpp/src/parquet/arrow/reader.cc:479
#15 0x000055555bf019df in parquet::arrow::ColumnReaderImpl::NextBatch 
(this=0x608000001020, batch_size=2089, out=0x7fffffffb740)
    at /home/antoine/arrow/dev/cpp/src/parquet/arrow/reader.cc:109
#16 0x000055555bf78829 in parquet::arrow::(anonymous 
namespace)::FileReaderImpl::ReadColumn (this=0x613000001a80, i=0, 
    row_groups=std::vector of length 1, capacity 1 = {...}, 
reader=0x608000001020, out=0x7fffffffb740)
    at /home/antoine/arrow/dev/cpp/src/parquet/arrow/reader.cc:285
#17 0x000055555bff1b9c in parquet::arrow::(anonymous 
namespace)::FileReaderImpl::DecodeRowGroups(std::shared_ptr<parquet::arrow::(anonymous
 namespace)::FileReaderImpl>, std::vector<int, std::allocator<int> > const&, 
std::vector<int, std::allocator<int> > const&, 
arrow::internal::Executor*)::$_4::operator()(unsigned long, 
std::shared_ptr<parquet::arrow::ColumnReaderImpl>) const (this=0x7fffffffbdc0, 
i=0, reader=warning: RTTI symbol not found for class 
'std::_Sp_counted_deleter<parquet::arrow::ColumnReaderImpl*, 
std::default_delete<parquet::arrow::ColumnReaderImpl>, std::allocator<void>, 
(__gnu_cxx::_Lock_policy)2>'
warning: RTTI symbol not found for class 
'std::_Sp_counted_deleter<parquet::arrow::ColumnReaderImpl*, 
std::default_delete<parquet::arrow::ColumnReaderImpl>, std::allocator<void>, 
(__gnu_cxx::_Lock_policy)2>'

std::shared_ptr<parquet::arrow::ColumnReaderImpl> (use count 2, weak count 0) = 
{...}) at /home/antoine/arrow/dev/cpp/src/parquet/arrow/reader.cc:1236
#18 0x000055555bfed49d in 
arrow::internal::OptionalParallelForAsync<parquet::arrow::(anonymous 
namespace)::FileReaderImpl::DecodeRowGroups(std::shared_ptr<parquet::arrow::(anonymous
 namespace)::FileReaderImpl>, std::vector<int, std::allocator<int> > const&, 
std::vector<int, std::allocator<int> > const&, 
arrow::internal::Executor*)::$_4&, 
std::shared_ptr<parquet::arrow::ColumnReaderImpl>, 
std::shared_ptr<arrow::ChunkedArray> >(bool, 
std::vector<std::shared_ptr<parquet::arrow::ColumnReaderImpl>, 
std::allocator<std::shared_ptr<parquet::arrow::ColumnReaderImpl> > >, 
parquet::arrow::(anonymous 
namespace)::FileReaderImpl::DecodeRowGroups(std::shared_ptr<parquet::arrow::(anonymous
 namespace)::FileReaderImpl>, std::vector<int, std::allocator<int> > const&, 
std::vector<int, std::allocator<int> > const&, 
arrow::internal::Executor*)::$_4&, arrow::internal::Executor*) 
(use_threads=false, inputs=std::vector of length 1, capacity 1 = {...}, 
func=..., executor=0x604000002b90)
    at /home/antoine/arrow/dev/cpp/src/arrow/util/parallel.h:95
#19 0x000055555bfebe4c in parquet::arrow::(anonymous 
namespace)::FileReaderImpl::DecodeRowGroups (this=0x613000001a80, 
    self=std::shared_ptr<parquet::arrow::(anonymous namespace)::FileReaderImpl> 
(empty) = {...}, row_groups=std::vector of length 1, capacity 1 = {...}, 
    column_indices=std::vector of length 1, capacity 1 = {...}, 
cpu_executor=0x604000002b90) at 
/home/antoine/arrow/dev/cpp/src/parquet/arrow/reader.cc:1254
#20 0x000055555bee0d57 in parquet::arrow::(anonymous 
namespace)::FileReaderImpl::ReadRowGroups (this=0x613000001a80, 
    row_groups=std::vector of length 1, capacity 1 = {...}, 
column_indices=std::vector of length 1, capacity 1 = {...}, out=0x7fffffffc880)
    at /home/antoine/arrow/dev/cpp/src/parquet/arrow/reader.cc:1215
#21 0x000055555bedf948 in parquet::arrow::(anonymous 
namespace)::FileReaderImpl::ReadRowGroup (this=0x613000001a80, 
row_group_index=0, 
    column_indices=std::vector of length 1, capacity 1 = {...}, 
out=0x7fffffffc880) at 
/home/antoine/arrow/dev/cpp/src/parquet/arrow/reader.cc:322
#22 0x000055555bedfe9c in parquet::arrow::(anonymous 
namespace)::FileReaderImpl::ReadRowGroup (this=0x613000001a80, i=0, 
table=0x7fffffffc880)
    at /home/antoine/arrow/dev/cpp/src/parquet/arrow/reader.cc:326
#23 0x000055555becf902 in parquet::arrow::internal::FuzzReader 
(reader=std::unique_ptr<parquet::arrow::FileReader> = {...})
    at /home/antoine/arrow/dev/cpp/src/parquet/arrow/reader.cc:1338
#24 0x000055555bed0f66 in parquet::arrow::internal::FuzzReader 
(data=0x60e000000e40 " \377  \025", size=159)
    at /home/antoine/arrow/dev/cpp/src/parquet/arrow/reader.cc:1355
#25 0x000055555bec8b78 in LLVMFuzzerTestOneInput (data=0x60e000000e40 " \377  
\025", size=159) at /home/antoine/arrow/dev/cpp/src/parquet/arrow/fuzz.cc:22
#26 0x000055555bdef964 in fuzzer::Fuzzer::ExecuteCallback(unsigned char const*, 
unsigned long) ()
#27 0x000055555bdd9d30 in fuzzer::RunOneTest(fuzzer::Fuzzer*, char const*, 
unsigned long) ()
#28 0x000055555bddfa37 in fuzzer::FuzzerDriver(int*, char***, int (*)(unsigned 
char const*, unsigned long)) ()
#29 0x000055555be09053 in main ()
{code}




--
This message was sent by Atlassian Jira
(v8.20.10#820010)

Reply via email to