On Sat, 6 Oct 2007, Paul Menage wrote: > > The getting and putting of the tasks will prevent them from exiting or > > being deallocated prematurely. But this is also a critical section that > > will need to be protected by some mutex so it doesn't race with other > > set_cpus_allowed(). > > Is that necessary? If some other process calls set_cpus_allowed() > concurrently with a cpuset cpus update, it's not clear that there's > any defined serialization semantics that have to be achieved, as long > as the end result is that the task's cpus_allowed are within the > cpuset's cpus_allowed. > It can race with sched_setaffinity(). It has to give up tasklist_lock as well to call set_cpus_allowed() and can race cpus_allowed = cpuset_cpus_allowed(p); cpus_and(new_mask, new_mask, cpus_allowed); retval = set_cpus_allowed(p, new_mask); and allow a task to have a cpu outside of the cpuset's new cpus_allowed if you've taken it away between cpuset_cpus_allowed() and set_cpus_allowed(). David _______________________________________________ Containers mailing list Containers@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linux-foundation.org/mailman/listinfo/containers
