On Fri, 9 Jan 2026 15:21:19 -0500
Mathieu Desnoyers <[email protected]> wrote:
> * preempt disable/enable pair: 1.1 ns
> * srcu-fast lock/unlock: 1.5 ns
>
> CONFIG_RCU_REF_SCALE_TEST=y
> * migrate disable/enable pair: 3.0 ns
> * calls to migrate disable/enable pair within noinline functions: 17.0 ns
>
> CONFIG_RCU_REF_SCALE_TEST=m
> * migrate disable/enable pair: 22.0 ns
OUCH! So migrate disable/enable has a much larger overhead when executed in
a module than in the kernel? This means all spin_locks() in modules
converted to mutexes in PREEMPT_RT are taking this hit!
It looks like it has to allow access to the rq->nr_pinned. There's a hack to
expose this part of the rq struct for in-kernel by the following:
kernel/sched/rq-offsets.c: DEFINE(RQ_nr_pinned, offsetof(struct rq,
nr_pinned));
Then for the in-kernel code we have:
#define this_rq_raw() arch_raw_cpu_ptr(&runqueues)
#else
#define this_rq_raw() PERCPU_PTR(&runqueues)
#endif
#define this_rq_pinned() (*(unsigned int *)((void *)this_rq_raw() +
RQ_nr_pinned))
Looking at the scheduler code, the rq->nr_pinned is referenced by a static
function with:
static inline bool rq_has_pinned_tasks(struct rq *rq)
{
return rq->nr_pinned;
}
Which is only referenced in hotplug code and a balance_push() path in load
balancing. Does this variable really need to be in the runqueue struct?
Why not just make it a per-cpu variable. Maybe call it cpu_nr_pinned_tasks,
and export that for all to use?
It will not only fix the discrepancy between the overhead of
migrate_disable/enable in modules vs in-kernel. But it also removes the
hack to expose a portion of the runqueue.
-- Steve
