Commit f66e2727 authored by Kefeng Wang's avatar Kefeng Wang Committed by Andrew Morton
Browse files

mm: huge_memory: use folio_can_map_prot_numa() for pmd folio 

The folio_can_map_prot_numa() checks whether the folio can map prot numa,
which skips unsuitable folio, i.e.  zone device, shared folios (KSM, CoW),
non-movable dma pinned, dirty file folio and folios that already have the
expected node affinity.  Although the ksm only applies to small folios, an
extra test was added for large folios, but the other policies should be
applied to pmd folio, which helps to avoid unnecessary pmd change and
folio migration attempts.

Link: https://lkml.kernel.org/r/20251023113737.3572790-5-wangkefeng.wang@huawei.com


Signed-off-by: default avatarKefeng Wang <wangkefeng.wang@huawei.com>
Acked-by: default avatarDavid Hildenbrand <david@redhat.com>
Reviewed-by: default avatarSidhartha Kumar <sidhartha.kumar@oracle.com>
Reviewed-by: default avatarLorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent ca43034c

mm/huge_memory.c

+3 −14
Original line number Diff line number Diff line
@@ -2396,8 +2396,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, 
#endif



	if (prot_numa) {

		struct folio *folio;

		bool toptier;



		/*

		 * Avoid trapping faults against the zero page. The read-only

		 * data is likely to be read-cached on the local CPU and
@@ -2409,19 +2408,9 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, 
		if (pmd_protnone(*pmd))

			goto unlock;



		folio = pmd_folio(*pmd);

		toptier = node_is_toptier(folio_nid(folio));

		/*

		 * Skip scanning top tier node if normal numa

		 * balancing is disabled

		 */

		if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) &&

		    toptier)

		if (!folio_can_map_prot_numa(pmd_folio(*pmd), vma,

					     vma_is_single_threaded_private(vma)))

			goto unlock;



		if (folio_use_access_time(folio))

			folio_xchg_access_time(folio,

					       jiffies_to_msecs(jiffies));

	}

	/*

	 * In case prot_numa, we are under mmap_read_lock(mm). It's critical