From 085ff35e76368455c629b194bf3cb62dd82eadf6 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 17 Jan 2024 18:39:54 +0800 Subject: mm: memory: move mem_cgroup_charge() into alloc_anon_folio() The GFP flags from vma_thp_gfp_mask() according to user configuration only used for large folio allocation but not for memory cgroup charge, and GFP_KERNEL is used for both order-0 and large order folio when memory cgroup charge at present. However, mem_cgroup_charge() uses the GFP flags in a fairly sophisticated way. In addition to checking gfpflags_allow_blocking(), it pays attention to __GFP_NORETRY and __GFP_RETRY_MAYFAIL to ensure that processes within this memcg do not exceed their quotas. So we'd better to move mem_cgroup_charge() into alloc_anon_folio(), 1) it will make us to allocate as much as possible large order folio, because we could try the next order if mem_cgroup_charge() fails, although the memcg's memory usage is close to its limits. 2) using same GFP flags for allocation and charge is to be consistent with PMD THP firstly, in addition, according to GFP flag returned from vma_thp_gfp_mask(), GFP_TRANSHUGE_LIGHT could make us skip direct reclaim, _GFP_NORETRY will make us skip mem_cgroup_oom() and won't trigger memory cgroup oom from large order(order <= COSTLY_ORDER) folio charging. Link: https://lkml.kernel.org/r/20240122011612.501029-1-wangkefeng.wang@huawei.com Link: https://lkml.kernel.org/r/20240117103954.2756050-1-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Ryan Roberts Cc: David Hildenbrand Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Roman Gushchin Cc: Johannes Weiner Cc: Shakeel Butt Cc: Muchun Song Signed-off-by: Andrew Morton --- mm/memory.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index 5e608edfe330..00f3f4fbd131 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4173,8 +4173,8 @@ static bool pte_range_none(pte_t *pte, int nr_pages) static struct folio *alloc_anon_folio(struct vm_fault *vmf) { -#ifdef CONFIG_TRANSPARENT_HUGEPAGE struct vm_area_struct *vma = vmf->vma; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE unsigned long orders; struct folio *folio; unsigned long addr; @@ -4226,15 +4226,21 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf) addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); folio = vma_alloc_folio(gfp, order, vma, addr, true); if (folio) { + if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { + folio_put(folio); + goto next; + } + folio_throttle_swaprate(folio, gfp); clear_huge_page(&folio->page, vmf->address, 1 << order); return folio; } +next: order = next_order(&orders, order); } fallback: #endif - return vma_alloc_zeroed_movable_folio(vmf->vma, vmf->address); + return folio_prealloc(vma->vm_mm, vma, vmf->address, true); } /* @@ -4301,10 +4307,6 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) nr_pages = folio_nr_pages(folio); addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE); - if (mem_cgroup_charge(folio, vma->vm_mm, GFP_KERNEL)) - goto oom_free_page; - folio_throttle_swaprate(folio, GFP_KERNEL); - /* * The memory barrier inside __folio_mark_uptodate makes sure that * preceding stores to the page contents become visible before @@ -4358,8 +4360,6 @@ unlock: release: folio_put(folio); goto unlock; -oom_free_page: - folio_put(folio); oom: return VM_FAULT_OOM; } -- cgit v1.2.3-58-ga151