From e426b547700afbce3feb832635447b8d521d57d2 Mon Sep 17 00:00:00 2001 From: Dev Jain Date: Wed, 4 Jun 2025 16:05:37 +0800 Subject: [PATCH 1/2] mm: abstract THP allocation mainline inclusion from mainline-v6.10-rc1 commit ebcfc63d6bca3cce1bfca30092712f3468b4ecff category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/ICCFA0 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=ebcfc63d6bca3cce1bfca30092712f3468b4ecff -------------------------------- Patch series "Do not shatter hugezeropage on wp-fault", v7. It was observed at [1] and [2] that the current kernel behaviour of shattering a hugezeropage is inconsistent and suboptimal. For a VMA with a THP allowable order, when we write-fault on it, the kernel installs a PMD-mapped THP. On the other hand, if we first get a read fault, we get a PMD pointing to the hugezeropage; subsequent write will trigger a write-protection fault, shattering the hugezeropage into one writable page, and all the other PTEs write-protected. The conclusion being, as compared to the case of a single write-fault, applications have to suffer 512 extra page faults if they were to use the VMA as such, plus we get the overhead of khugepaged trying to replace that area with a THP anyway. Instead, replace the hugezeropage with a THP on wp-fault. [1]: https://lore.kernel.org/all/3743d7e1-0b79-4eaf-82d5-d1ca29fe347d@arm.com/ [2]: https://lore.kernel.org/all/1cfae0c0-96a2-4308-9c62-f7a640520242@arm.com/ This patch (of 2): In preparation for the second patch, abstract away the THP allocation logic present in the create_huge_pmd() path, which corresponds to the faulting case when no page is present. There should be no functional change as a result of applying this patch, except that, as David notes at [1], a PMD-aligned address should be passed to update_mmu_cache_pmd(). [1]: https://lore.kernel.org/all/ddd3fcd2-48b3-4170-bcaa-2fe66e093f43@redhat.com/ Link: https://lkml.kernel.org/r/20241008061746.285961-1-dev.jain@arm.com Link: https://lkml.kernel.org/r/20241008061746.285961-2-dev.jain@arm.com Signed-off-by: Dev Jain Acked-by: David Hildenbrand Reviewed-by: Kefeng Wang Cc: Alistair Popple Cc: Aneesh Kumar K.V Cc: Anshuman Khandual Cc: Barry Song Cc: Catalin Marinas Cc: Christoph Lameter Cc: Dave Hansen Cc: Hugh Dickins Cc: Jan Kara Cc: Kirill A. Shutemov Cc: Lance Yang Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michal Hocko Cc: Peter Xu Cc: Ryan Roberts Cc: Vlastimil Babka Cc: Will Deacon Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton Conflicts: mm/huge_memory.c [Context conflicts in huge_memory.c due to miss commit dafff3f4c850, and still use clear_huge_page to avoid introduce commit 78fefd04c123 and so on. meanwhile move add_reliable_page_counter to map_anon_folio_pmd because hulk commit 8fc2546f8508 introduce it] Signed-off-by: Wang Lian --- mm/huge_memory.c | 100 +++++++++++++++++++++++++++-------------------- 1 file changed, 58 insertions(+), 42 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 7045b7b7ac4a..38be4b0b1202 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1310,47 +1310,82 @@ unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, } EXPORT_SYMBOL_GPL(thp_get_unmapped_area); -static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, - struct page *page, gfp_t gfp) +static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma, + unsigned long addr) { - struct vm_area_struct *vma = vmf->vma; - struct folio *folio = page_folio(page); - pgtable_t pgtable; - unsigned long haddr = vmf->address & HPAGE_PMD_MASK; - vm_fault_t ret = 0; + gfp_t gfp = vma_thp_gfp_mask(vma); + const int order = HPAGE_PMD_ORDER; + struct folio *folio; - VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); + folio = vma_alloc_folio(gfp, order, vma, addr & HPAGE_PMD_MASK, true); + if (unlikely(!folio)) { + count_vm_event(THP_FAULT_FALLBACK); + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); + return NULL; + } + + VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { folio_put(folio); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); - count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK); - count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); - return VM_FAULT_FALLBACK; + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); + return NULL; } folio_throttle_swaprate(folio, gfp); - pgtable = pte_alloc_one(vma->vm_mm); - if (unlikely(!pgtable)) { - ret = VM_FAULT_OOM; - goto release; - } - - clear_huge_page(page, vmf->address, HPAGE_PMD_NR); + clear_huge_page(&folio->page, addr, HPAGE_PMD_NR); /* * The memory barrier inside __folio_mark_uptodate makes sure that * clear_huge_page writes become visible before the set_pmd_at() * write. */ __folio_mark_uptodate(folio); + return folio; +} + +static void map_anon_folio_pmd(struct folio *folio, pmd_t *pmd, + struct vm_area_struct *vma, unsigned long haddr) +{ + pmd_t entry; + + entry = mk_huge_pmd(&folio->page, vma->vm_page_prot); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + folio_add_new_anon_rmap(folio, vma, haddr, RMAP_EXCLUSIVE); + folio_add_lru_vma(folio, vma); + set_pmd_at(vma->vm_mm, haddr, pmd, entry); + update_mmu_cache_pmd(vma, haddr, pmd); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); + add_reliable_folio_counter(folio, vma->vm_mm, HPAGE_PMD_NR); + count_vm_event(THP_FAULT_ALLOC); + count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC); + count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); +} + +static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf) +{ + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + struct vm_area_struct *vma = vmf->vma; + struct folio *folio; + pgtable_t pgtable; + vm_fault_t ret = 0; + + folio = vma_alloc_anon_folio_pmd(vma, vmf->address); + if (unlikely(!folio)) + return VM_FAULT_FALLBACK; + + pgtable = pte_alloc_one(vma->vm_mm); + if (unlikely(!pgtable)) { + ret = VM_FAULT_OOM; + goto release; + } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) { goto unlock_release; } else { - pmd_t entry; - ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock_release; @@ -1364,21 +1399,10 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, VM_BUG_ON(ret & VM_FAULT_FALLBACK); return ret; } - - entry = mk_huge_pmd(page, vma->vm_page_prot); - entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - folio_add_new_anon_rmap(folio, vma, haddr, RMAP_EXCLUSIVE); - folio_add_lru_vma(folio, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); - set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); - update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); - add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); - add_reliable_page_counter(page, vma->vm_mm, HPAGE_PMD_NR); + map_anon_folio_pmd(folio, vmf->pmd, vma, haddr); mm_inc_nr_ptes(vma->vm_mm); spin_unlock(vmf->ptl); - count_vm_event(THP_FAULT_ALLOC); - count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC); - count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); } return 0; @@ -1445,8 +1469,6 @@ static void set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; - gfp_t gfp; - struct folio *folio; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; vm_fault_t ret; @@ -1496,14 +1518,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) } return ret; } - gfp = vma_thp_gfp_mask(vma); - folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, vma, haddr, true); - if (unlikely(!folio)) { - count_vm_event(THP_FAULT_FALLBACK); - count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK); - return VM_FAULT_FALLBACK; - } - return __do_huge_pmd_anonymous_page(vmf, &folio->page, gfp); + + return __do_huge_pmd_anonymous_page(vmf); } static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, -- Gitee From fcd7c0f07916cf86f2c06fae01bf9fc9155913d6 Mon Sep 17 00:00:00 2001 From: Dev Jain Date: Wed, 4 Jun 2025 16:35:47 +0800 Subject: [PATCH 2/2] mm: allocate THP on hugezeropage wp-fault mainline inclusion from mainline-v6.10-rc1 commit 1ced09e0331f6cc4ca7eae75bc0ef03957129a94 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/ICCFA0 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=1ced09e0331f6cc4ca7eae75bc0ef03957129a94 -------------------------------- Introduce do_huge_zero_wp_pmd() to handle wp-fault on a hugezeropage and replace it with a PMD-mapped THP. Remember to flush TLB entry corresponding to the hugezeropage. In case of failure, fallback to splitting the PMD. Link: https://lkml.kernel.org/r/20241008061746.285961-3-dev.jain@arm.com Signed-off-by: Dev Jain Acked-by: David Hildenbrand Reviewed-by: Kefeng Wang Cc: Alistair Popple Cc: Aneesh Kumar K.V Cc: Anshuman Khandual Cc: Barry Song Cc: Catalin Marinas Cc: Christoph Lameter Cc: Dave Hansen Cc: Dev Jain Cc: Hugh Dickins Cc: Jan Kara Cc: Kirill A. Shutemov Cc: Lance Yang Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michal Hocko Cc: Peter Xu Cc: Ryan Roberts Cc: Vlastimil Babka Cc: Will Deacon Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Wang Lian --- mm/huge_memory.c | 41 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 40 insertions(+), 1 deletion(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 38be4b0b1202..9af90b53ab0a 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1979,6 +1979,38 @@ void huge_pmd_set_accessed(struct vm_fault *vmf) spin_unlock(vmf->ptl); } +static vm_fault_t do_huge_zero_wp_pmd(struct vm_fault *vmf) +{ + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + struct vm_area_struct *vma = vmf->vma; + struct mmu_notifier_range range; + struct folio *folio; + vm_fault_t ret = 0; + + folio = vma_alloc_anon_folio_pmd(vma, vmf->address); + if (unlikely(!folio)) + return VM_FAULT_FALLBACK; + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, haddr, + haddr + HPAGE_PMD_SIZE); + mmu_notifier_invalidate_range_start(&range); + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_same(pmdp_get(vmf->pmd), vmf->orig_pmd))) + goto release; + ret = check_stable_address_space(vma->vm_mm); + if (ret) + goto release; + (void)pmdp_huge_clear_flush(vma, haddr, vmf->pmd); + map_anon_folio_pmd(folio, vmf->pmd, vma, haddr); + goto unlock; +release: + folio_put(folio); +unlock: + spin_unlock(vmf->ptl); + mmu_notifier_invalidate_range_end(&range); + return ret; +} + vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) { const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; @@ -1991,8 +2023,15 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd); VM_BUG_ON_VMA(!vma->anon_vma, vma); - if (is_huge_zero_pmd(orig_pmd)) + if (is_huge_zero_pmd(orig_pmd)) { + vm_fault_t ret = do_huge_zero_wp_pmd(vmf); + + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + + /* Fallback to splitting PMD if THP cannot be allocated */ goto fallback; + } spin_lock(vmf->ptl); -- Gitee