Oleg reported that on architectures with
__ARCH_WANT_INTERRUPTS_ON_CTXSW the IPI from
task_oncpu_function_call() can land before perf_event_task_sched_in()
and cause interesting situations for eg. perf_install_in_context().
This patch reworks the task_oncpu_function_call() interface to give a
more usable primitive as well as rework all its users to hopefully be
more obvious as well as remove the races.
While looking at the code I also found a number of races against
perf_event_task_sched_out() which can flip contexts between tasks so
plug those too.