On Fri 23-05-25 15:44:37, Aboorva Devarajan wrote: > While this change may introduce some lock contention, it only affects > the task_mem function which is invoked only when reading > /proc/[pid]/status. Since this is not on a performance critical path, > it will be good to have this change in order to get accurate memory > stats. This particular function might not be performance critical but you are exposing a lock contention to the userspace that could be abused and cause contention controlled by unprivileged user. I do not think we want that without any control. Or is the pcp lock not really affecting any actual kernel code path? So while precision is nice it should be weight against potential side effects. -- Michal Hocko SUSE Labs
