Skip to content

fix: avoid signed integer overflow UB in BloomFilter and DeltaVarintCompressor #329

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
lxy-9602 merged 3 commits into from
Jun 2, 2026
Merged

fix: avoid signed integer overflow UB in BloomFilter and DeltaVarintCompressor #329

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4c729f5
fix: avoid signed integer overflow UB in BloomFilter and DeltaVarintC…
lxy-9602 Jun 2, 2026
efc360e
fix clang
lxy-9602 Jun 2, 2026
a7815da
Merge branch 'main' into fix-hash-ub
lxy-9602 Jun 2, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions src/paimon/common/utils/bloom_filter.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,10 @@ Status BloomFilter::AddHash(int32_t hash1) {
auto hash2 = static_cast<int32_t>(static_cast<uint32_t>(hash1) >> 16);

for (int32_t i = 1; i <= num_hash_functions_; i++) {
int32_t combined_hash = hash1 + (i * hash2);
// Use uint32_t arithmetic to avoid signed overflow UB (matches Java int wrap semantics)
auto combined_hash =
static_cast<int32_t>(static_cast<uint32_t>(hash1) +
(static_cast<uint32_t>(i) * static_cast<uint32_t>(hash2)));
// hashcode should be positive, flip all the bits if it's negative
if (combined_hash < 0) {
combined_hash = ~combined_hash;
Expand All @@ -74,7 +77,10 @@ bool BloomFilter::TestHash(int32_t hash1) const {
auto hash2 = static_cast<int32_t>(static_cast<uint32_t>(hash1) >> 16);

for (int32_t i = 1; i <= num_hash_functions_; i++) {
int32_t combined_hash = hash1 + (i * hash2);
// Use uint32_t arithmetic to avoid signed overflow UB (matches Java int wrap semantics)
auto combined_hash =
static_cast<int32_t>(static_cast<uint32_t>(hash1) +
(static_cast<uint32_t>(i) * static_cast<uint32_t>(hash2)));
// hashcode should be positive, flip all the bits if it's negative
if (combined_hash < 0) {
combined_hash = ~combined_hash;
Expand Down
10 changes: 8 additions & 2 deletions src/paimon/common/utils/bloom_filter64.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,10 @@ void BloomFilter64::AddHash(int64_t hash64) {
auto hash2 = static_cast<int32_t>(static_cast<uint64_t>(hash64) >> 32);

for (int32_t i = 1; i <= num_hash_functions_; i++) {
int32_t combined_hash = hash1 + (i * hash2);
// Use uint32_t arithmetic to avoid signed overflow UB (matches Java int wrap semantics)
auto combined_hash =
static_cast<int32_t>(static_cast<uint32_t>(hash1) +
(static_cast<uint32_t>(i) * static_cast<uint32_t>(hash2)));
// hashcode should be positive, flip all the bits if it's negative
if (combined_hash < 0) {
combined_hash = ~combined_hash;
Expand All @@ -83,7 +86,10 @@ bool BloomFilter64::TestHash(int64_t hash64) const {
auto hash2 = static_cast<int32_t>(static_cast<uint64_t>(hash64) >> 32);

for (int32_t i = 1; i <= num_hash_functions_; i++) {
int32_t combined_hash = hash1 + (i * hash2);
// Use uint32_t arithmetic to avoid signed overflow UB (matches Java int wrap semantics)
auto combined_hash =
static_cast<int32_t>(static_cast<uint32_t>(hash1) +
(static_cast<uint32_t>(i) * static_cast<uint32_t>(hash2)));
// hashcode should be positive, flip all the bits if it's negative
if (combined_hash < 0) {
combined_hash = ~combined_hash;
Expand Down
12 changes: 8 additions & 4 deletions src/paimon/common/utils/delta_varint_compressor.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,12 +30,14 @@ std::vector<char> DeltaVarintCompressor::Compress(const std::vector<int64_t>& da
return {};
}

// 1. Delta encoding
// 1. Delta encoding (use unsigned subtraction to avoid signed overflow UB)
std::vector<int64_t> deltas;
deltas.reserve(data.size());
deltas.push_back(data[0]);
for (size_t i = 1; i < data.size(); i++) {
deltas.push_back(data[i] - data[i - 1]);
uint64_t unsigned_delta =
static_cast<uint64_t>(data[i]) - static_cast<uint64_t>(data[i - 1]);
deltas.push_back(static_cast<int64_t>(unsigned_delta));
}

// 2. ZigZag + Varint
Expand All @@ -61,11 +63,13 @@ Result<std::vector<int64_t>> DeltaVarintCompressor::Decompress(const std::vector
deltas.push_back(delta);
}

// 2. Delta decoding
// 2. Delta decoding (use unsigned addition to avoid signed overflow UB)
std::vector<int64_t> result(deltas.size());
result[0] = deltas[0];
for (size_t i = 1; i < result.size(); i++) {
result[i] = result[i - 1] + deltas[i];
uint64_t reconstructed =
static_cast<uint64_t>(result[i - 1]) + static_cast<uint64_t>(deltas[i]);
result[i] = static_cast<int64_t>(reconstructed);
}
return result;
}
Expand Down
Loading