Re: [PATCH] mm/ksm: do not inherit ksm_zero_pages counter or PTE markers on fork
From: Xu Xin (vivo)
Date: Thu Nov 19 2026 - 21:10:42 EST
> >> But ... they were placed by KSM?
> >>
> >> Just like any other KSM folios deduplicated before fork and then shared with the
> >> child?
> >
> > I see your point, but in practice, people evaluating use_zero_pages=1 often
> > look at ksm_zero_pages to gauge how much memory KSM actually saved. Since
> > forked pages already share the same physical frame via COW even without KSM,
> > counting them across many forked children can give a somewhat misleading
> > impression of KSM's actual savings.
> >
> > Also, ksm_merging_pages right next to it is already reset to 0 on fork (even
> > when regular KSM folios are shared with the child), so resetting ksm_zero_pages
> > keeps the two counters consistent.
> >
> >>
> >> So won't there be an inconsistency when MADV_UNMERGEABLE?
> >>
> >
> > As for MADV_UNMERGEABLE, leaving the child's mapping as a normal read-only shared
> > zero page is safe and avoids extra allocations. Plus it naturally avoids the
> > skipped-VMA (MADV_DONTFORK) accounting bug you spotted, and does so
> > without extra per-PTE overhead.
> >
> > What do you think?
>
> We should then definitely document the behavioral change, and how ksm_zero_pages
> interacts with fork.
Agreed, I'll update these changes into documents.
>
> For clearing the dirty bit we should have a dedicated helper, such the handling
> is hidden like in is_ksm_zero_pte().
>
>
> So clean up that code (reducing the code comment drastically) and properly
> document all that for ksm_zero_pages.
Ok, Will do it in v2 together with the fix of building error when CONFIG_KSM is not set.