On Tue, Sep 3, 2019 at 1:11 PM Mathieu Desnoyers <[email protected]> wrote: > > + cpus_read_lock(); > + for_each_online_cpu(cpu) {
This would likely be better off using mm_cpumask(mm) instead of all
online CPU's.
Plus doing the rcu_read_lock() inside the loop seems pointless. Even
with a lot of cores, it's not going to loop _that_ many times for RCU
latency to be an issue.
Linus
