Re: [PATCH 2/3] mm/page_alloc: remove IRQ saving/restoring from pcp locking

[Johannes Weiner]

On Fri, Feb 27, 2026 at 06:07:59PM +0100, Vlastimil Babka wrote:
> Effectively revert commit 038a102535eb ("mm/page_alloc: prevent pcp
> corruption with SMP=n"). The original problem is now avoided by
> pcp_spin_trylock() always failing on CONFIG_SMP=n, so we do not need to
> disable IRQs anymore.
> 
> It's not a complete revert, because keeping the pcp_spin_(un)lock()
> wrappers is useful. Rename them from _maybe_irqsave/restore to _nopin.
> The difference from pcp_spin_trylock()/pcp_spin_unlock() is that the
> _nopin variants don't perform pcpu_task_pin/unpin().
> 
> Signed-off-by: Vlastimil Babka (SUSE) <vbabka@xxxxxxxxxx>

Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>