Re: [PATCH] mm: Optimize TLB flushes during page reclaim

[Rik van Riel]

On Thu, 2025-01-23 at 13:16 -0600, Vinay Banakar wrote:
> 
> I initially assumed that all paths leading to shrink_folio_list()
> submitted 512 pages at a time. Turns out this is only true for the
> madvise path.
> The other paths have different batch sizes:
> - shrink_inactive_list(): Uses SWAP_CLUSTER_MAX (32 pages)
> - evict_folios(): Varies between 64 and 4096 pages (MGLRU)
> - damon_pa_pageout(): Variable size based on DAMON region
> - reclaim_clean_pages_from_list(): Clean pages only, unaffected by
> this patch
> 
> We have two options:
> 1. Keep the current logic where TLB flush batching varies by caller
> 2. Enforce consistent 512-page batching in shrink_folio_list() and
> also convert to folio_batch as suggested by Matthew

My preference would be to fix one thing at a time,
and simply remove the comments that suggest everything
is done at PMD level.

I'll ACK the patch if the misleading comments and
changelog text are removed or fixed up :)

-- 
All Rights Reversed.