Re: [PATCH v5 5/5] mm/vmscan: flush TLB for every 31 folios evictions

[Zhang Peng]

On Fri, Aug 14, 2026 at 5:58 AM Barry Song <baohua@xxxxxxxxxx> wrote:
>
> Yes, I think batching the dirty flush is a great idea. I can clearly
> see that IPIs for dirty flushes (smp_call) on x86 take up a
> significant part of the flame graph when building the kernel in a
> memcg, so I think this is something we should pursue. Could we
> revisit this patch after we clean up the previous ones?

Sounds good, and thanks for confirming the workload - useful to know
the dirty-flush IPIs show up that clearly in a memcg kernel build.

I've split the series accordingly. The four cleanup patches, with the
explicit-outcome rework you asked for in 2/5 and 3/5, are posted on
their own as:

  [PATCH 0/4] mm/vmscan: refactor shrink_folio_list()
  https://lore.kernel.org/all/20260920-vmscan-refactor-v1-0-ec04d71cb761@xxxxxxxxxxx/

No functional change intended there. I'll repost the TLB batching on
top once that has settled.

Thanks
Zhang Peng