Re: [RFC PATCH 3/3] KVM: x86/mmu: skip zap maybe-dma-pinned pages for NUMA migration

[Yan Zhao]

On Tue, Aug 08, 2023 at 04:56:11PM -0700, Sean Christopherson wrote:
 
> and then for PG_anon_exclusive
> 
> 	 * ... For now, we only expect it to be
> 	 * set on tail pages for PTE-mapped THP.
> 	 */
> 	PG_anon_exclusive = PG_mappedtodisk,
> 

	/*
         * Depending on the way an anonymous folio can be mapped into a page
         * table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped
         * THP), PG_anon_exclusive may be set only for the head page or for
         * tail pages of an anonymous folio. For now, we only expect it to be
         * set on tail pages for PTE-mapped THP.
         */
        PG_anon_exclusive = PG_mappedtodisk,

Now sure why the comment says PG_anon_exclusive is set only on tail
pages for PTE-mapped THP,

what I observed is that only head page of a compound page is set to
anon_exclusive.

And the code path is here:
__handle_mm_fault
  |->create_huge_pmd
     |->do_huge_pmd_anonymous_page //if (vma_is_anonymous(vmf->vma)
     	|->folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, vma, haddr, true);
        |->__do_huge_pmd_anonymous_page(vmf, &folio->page, gfp);
           |->folio_add_new_anon_rmap
              |->__page_set_anon_rmap(folio, &folio->page, vma, address, 1);
	         |->SetPageAnonExclusive(page)

And this code path has been present since
6c287605fd56 ("mm: remember exclusively mapped anonymous pages with PG_anon_exclusive")