CPU_MASK
cpu_id = read_cpuid_id() & CPU_MASK;
times_index = percpu_times_index[cpu & CPU_MASK] % NR_SLOTS;
percpu_times[cpu & CPU_MASK][times_index] = bpf_ktime_get_ns() - start_time;
percpu_times_index[cpu & CPU_MASK] += 1;
#define MAX_CPUS (CPU_MASK + 1) /* should match MAX_BUCKETS in benchs/bench_trigger.c */
__sync_add_and_fetch(&hits[cpu & CPU_MASK].value, 1);