On Thu, Jul 23, 2020 at 11:06:48AM -0700, Song Liu wrote: > + pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, > + 0 /* cpu 0 */, -1 /* group id */, > + 0 /* flags */); > + if (pmu_fd < 0 && errno == ENOENT) { > + printf("%s:SKIP:cannot open PERF_COUNT_HW_CPU_CYCLES with precise_ip > 0\n", > + __func__); > + test__skip(); > + goto cleanup; > + } That wasn't enough in my test VM. I've changed it to be: (errno == ENOENT || errno == EOPNOTSUPP) and applied the set. Thanks