From c299a2285d9d8bda4da024455de65e3d00de6f17 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Tue, 4 Aug 2026 17:04:27 -0400 Subject: [PATCH] mm/huge_memory: use folio's memcg inside __folio_split() Patch series "Honor XA_FLAGS_ACCOUNT in xas_split_alloc() and charge to folio's memcg", v3. __GFP_ACCOUNT is needed for xarray node allocation accounting when XA_FLAGS_ACCOUNT is set. Commit 7b785645e8f13 ("mm: fix page cache convergence regression") fixed a workingset regression with it. xas_split_alloc() does not have it and needs to be fixed. In addition, based on Sashiko's review[1] and Johannes' confirmation[2], to charge the right memcg, folio's memcg needs to be active during folio split. Add that before adding __GFP_ACCOUNT. There is no workingset convergence regression related to missing __GFP_ACCOUNT in xas_split_alloc() and the impact to userspace should be minor. This patch (of 2): During a pagecache folio split, an xarray node allocation can happen and needs to charge at folio's memcg instead of folio split invoker's memcg, because for example folio split can happen during reclaim and reclaim's active memcg might not be folio's memcg. Switch to folio's memcg at the beginning and switch back afterwards. Link: https://lore.kernel.org/20260804-add-gfp_account-to-xas_split_alloc-v3-0-38cb3ff325c5@nvidia.com Link: https://lore.kernel.org/20260804-add-gfp_account-to-xas_split_alloc-v3-1-38cb3ff325c5@nvidia.com Link: https://sashiko.dev/#/patchset/20260727-add-gfp_account-to-xas_split_alloc-v1-1-9fae6bf64838%40nvidia.com?part=1 [1] Link: https://lore.kernel.org/all/amtcBZ-_QVRgCd6b@cmpxchg.org/ [2] Fixes: 6b24ca4a1a8d ("mm: Use multi-index entries in the page cache") Signed-off-by: Zi Yan Suggested-by: Johannes Weiner Reviewed-by: Baolin Wang Acked-by: Lorenzo Stoakes (ARM) Acked-by: Johannes Weiner Cc: Barry Song Cc: David Hildenbrand Cc: Dev Jain Cc: Lance Yang Cc: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Ryan Roberts Cc: William Kucharski Cc: Signed-off-by: Andrew Morton --- mm/huge_memory.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index a8174d1d3848..ced400f72d43 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -4105,34 +4105,42 @@ static int __folio_split(struct folio *folio, unsigned int new_order, XA_STATE(xas, &folio->mapping->i_pages, folio->index); struct folio *end_folio = folio_next(folio); bool is_anon = folio_test_anon(folio); + struct mem_cgroup *memcg, *old_memcg; struct address_space *mapping = NULL; struct anon_vma *anon_vma = NULL; int old_order = folio_order(folio); struct folio *new_folio, *next; int nr_shmem_dropped = 0; enum ttu_flags ttu_flags = 0; - int ret; pgoff_t end = 0; + int ret; VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio); VM_WARN_ON_ONCE_FOLIO(!folio_test_large(folio), folio); if (folio != page_folio(split_at) || folio != page_folio(lock_at)) { ret = -EINVAL; - goto out; + goto out_no_memcg; } if (new_order >= old_order) { ret = -EINVAL; - goto out; + goto out_no_memcg; } ret = folio_check_splittable(folio, new_order, split_type); if (ret) { VM_WARN_ONCE(ret == -EINVAL, "Tried to split an unsplittable folio"); - goto out; + goto out_no_memcg; } + /* + * switch to folio's memcg as xarray node allocation can happen and + * needs to charge to it. + */ + memcg = get_mem_cgroup_from_folio(folio); + old_memcg = set_active_memcg(memcg); + if (is_anon) { /* * The caller does not necessarily hold an mmap_lock that would @@ -4275,6 +4283,10 @@ static int __folio_split(struct folio *folio, unsigned int new_order, if (mapping) i_mmap_unlock_read(mapping); out: + /* restore to caller's old_memcg */ + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); +out_no_memcg: xas_destroy(&xas); if (is_pmd_order(old_order)) count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED);