On 5/25/21 3:04 PM, Mel Gorman wrote:

On Tue, May 25, 2021 at 01:39:30AM +0200, Vlastimil Babka wrote:

quoted

As another step of shortening irq disabled sections in ___slab_alloc(), don't
disable irqs until doing initial checks if there is a cached percpu slab and
it's suitable for our allocation.

Now we have to recheck c->page after actually disabling irqs as an allocation
in irq might have replaced it.

Signed-off-by: Vlastimil Babka <redacted>

Minor nit only -- consider adding a comment at the new_slab label that
IRQs must be disabled already.

Good point, will use lockdep_assert_irqs_disabled() as that's a functional comment.

Acked-by: Mel Gorman <redacted>

Thanks.