Re: [PATCH] mm/mmu_notifier: Remove non_block_start/end() from notifier invocation

[Jason Gunthorpe]

On Wed, Aug 12, 2026 at 06:04:47PM +0200, Paolo Bonzini wrote:
> > + * Atomic-flavor readers run with preemption disabled, so every
> > + * read-side critical section is bounded and running (not blocked) on
> > + * some CPU, which is what makes spinning here sane: the wait is
> > + * bounded by the longest such section. No index flip and no
> > + * grace-period sequence update occur, so concurrent call_srcu(),
> > + * synchronize_srcu() and srcu_barrier() are entirely unaffected.
> 
> Making synchronize_srcu_atomic() spin in CONFIG_PREEMPT_RT is a
> slightly tall request - it's basically putting it on the same level as
> raw_spinlock. But if the MMU notifier guys really want to make OOM
> notifiers atomic, this would be basically the only way to do so.

IMHO it is fine if PREEMPT_RT does something else, just that the
normal cases should follow the current arrangment where it is atomic

> If instead it's okay to remove nonblock_start/end under
> CONFIG_PREEMPT_RT, for RT kernels I'd rather avoid

This seems well agreed at least

Jason