Re: [RFC 04/26] mm, slub: simplify kmem_cache_cpu and tid setup

From: Mel Gorman
Date: Tue May 25 2021 - 07:47:21 EST

On Tue, May 25, 2021 at 01:39:24AM +0200, Vlastimil Babka wrote:
> In slab_alloc_node() and do_slab_free() fastpaths we need to guarantee that
> our kmem_cache_cpu pointer is from the same cpu as the tid value. Currently
> that's done by reading the tid first using this_cpu_read(), then the
> kmem_cache_cpu pointer and verifying we read the same tid using the pointer and
> plain READ_ONCE().
> This can be simplified to just fetching kmem_cache_cpu pointer and then reading
> tid using the pointer. That guarantees they are from the same cpu. We don't
> need to read the tid using this_cpu_read() because the value will be validated
> by this_cpu_cmpxchg_double(), making sure we are on the correct cpu and the
> freelist didn't change by anyone preempting us since reading the tid.
> Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx>

Wow, that's a fun approach to avoiding disabling preemption but the
validation check against preemption remains the same so;

Acked-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>

Mel Gorman