Prominent Linux engineer Peter Zijlstra at Intel adapted the FUTEX code to use a RCU-based, per-CPU reference counting to address a performance bottleneck found within the existing code that used a single instance variant.
Peter explained with the patch addressing the FUTEX performance bottleneck:
"The use of rcuref_t for reference counting introduces a performance bottleneck when accessed concurrently by multiple threads during futex operations.
Replace rcuref_t with special crafted per-CPU reference counters. The lifetime logic remains the same.
The newly allocate private hash starts in FR_PERCPU state. In this state, each futex operation that requires the private hash uses a per-CPU counter (an unsigned int) for incrementing or decrementing the reference count."
The FUTEX improvements were merged last week to Linux 6.17 Git as part of the locking/futex pull request.