The patch titled Subject: mm: do_zap_pte_range: return any_skipped information to the caller has been added to the -mm mm-unstable branch. Its filename is mm-do_zap_pte_range-return-any_skipped-information-to-the-caller.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-do_zap_pte_range-return-any_skipped-information-to-the-caller.patch This patch will later appear in the mm-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Qi Zheng <zhengqi.arch@xxxxxxxxxxxxx> Subject: mm: do_zap_pte_range: return any_skipped information to the caller Date: Wed, 4 Dec 2024 19:09:47 +0800 Let the caller of do_zap_pte_range() know whether we skip zap ptes or reinstall uffd-wp ptes through any_skipped parameter, so that subsequent commits can use this information in zap_pte_range() to detect whether the PTE page can be reclaimed. Link: https://lkml.kernel.org/r/59f33ec9f74e9f058ed319b0bfadd76b0f7adf9b.1733305182.git.zhengqi.arch@xxxxxxxxxxxxx Signed-off-by: Qi Zheng <zhengqi.arch@xxxxxxxxxxxxx> Cc: Andy Lutomirski <luto@xxxxxxxxxx> Cc: Catalin Marinas <catalin.marinas@xxxxxxx> Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx> Cc: David Hildenbrand <david@xxxxxxxxxx> Cc: David Rientjes <rientjes@xxxxxxxxxx> Cc: Hugh Dickins <hughd@xxxxxxxxxx> Cc: Jann Horn <jannh@xxxxxxxxxx> Cc: Lorenzo Stoakes <lorenzo.stoakes@xxxxxxxxxx> Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx> Cc: Mel Gorman <mgorman@xxxxxxx> Cc: Muchun Song <muchun.song@xxxxxxxxx> Cc: Peter Xu <peterx@xxxxxxxxxx> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Cc: Will Deacon <will@xxxxxxxxxx> Cc: Zach O'Keefe <zokeefe@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/memory.c | 36 +++++++++++++++++++++--------------- 1 file changed, 21 insertions(+), 15 deletions(-) --- a/mm/memory.c~mm-do_zap_pte_range-return-any_skipped-information-to-the-caller +++ a/mm/memory.c @@ -1501,7 +1501,7 @@ static __always_inline void zap_present_ struct vm_area_struct *vma, struct folio *folio, struct page *page, pte_t *pte, pte_t ptent, unsigned int nr, unsigned long addr, struct zap_details *details, int *rss, - bool *force_flush, bool *force_break) + bool *force_flush, bool *force_break, bool *any_skipped) { struct mm_struct *mm = tlb->mm; bool delay_rmap = false; @@ -1527,8 +1527,8 @@ static __always_inline void zap_present_ arch_check_zapped_pte(vma, ptent); tlb_remove_tlb_entries(tlb, pte, nr, addr); if (unlikely(userfaultfd_pte_wp(vma, ptent))) - zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, - ptent); + *any_skipped = zap_install_uffd_wp_if_needed(vma, addr, pte, + nr, details, ptent); if (!delay_rmap) { folio_remove_rmap_ptes(folio, page, nr, vma); @@ -1552,7 +1552,7 @@ static inline int zap_present_ptes(struc struct vm_area_struct *vma, pte_t *pte, pte_t ptent, unsigned int max_nr, unsigned long addr, struct zap_details *details, int *rss, bool *force_flush, - bool *force_break) + bool *force_break, bool *any_skipped) { const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; struct mm_struct *mm = tlb->mm; @@ -1567,15 +1567,17 @@ static inline int zap_present_ptes(struc arch_check_zapped_pte(vma, ptent); tlb_remove_tlb_entry(tlb, pte, addr); if (userfaultfd_pte_wp(vma, ptent)) - zap_install_uffd_wp_if_needed(vma, addr, pte, 1, - details, ptent); + *any_skipped = zap_install_uffd_wp_if_needed(vma, addr, + pte, 1, details, ptent); ksm_might_unmap_zero_page(mm, ptent); return 1; } folio = page_folio(page); - if (unlikely(!should_zap_folio(details, folio))) + if (unlikely(!should_zap_folio(details, folio))) { + *any_skipped = true; return 1; + } /* * Make sure that the common "small folio" case is as fast as possible @@ -1587,22 +1589,23 @@ static inline int zap_present_ptes(struc zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr, addr, details, rss, force_flush, - force_break); + force_break, any_skipped); return nr; } zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, 1, addr, - details, rss, force_flush, force_break); + details, rss, force_flush, force_break, any_skipped); return 1; } static inline int zap_nonpresent_ptes(struct mmu_gather *tlb, struct vm_area_struct *vma, pte_t *pte, pte_t ptent, unsigned int max_nr, unsigned long addr, - struct zap_details *details, int *rss) + struct zap_details *details, int *rss, bool *any_skipped) { swp_entry_t entry; int nr = 1; + *any_skipped = true; entry = pte_to_swp_entry(ptent); if (is_device_private_entry(entry) || is_device_exclusive_entry(entry)) { @@ -1660,7 +1663,7 @@ static inline int zap_nonpresent_ptes(st WARN_ON_ONCE(1); } clear_not_present_full_ptes(vma->vm_mm, addr, pte, nr, tlb->fullmm); - zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent); + *any_skipped = zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent); return nr; } @@ -1669,7 +1672,8 @@ static inline int do_zap_pte_range(struc struct vm_area_struct *vma, pte_t *pte, unsigned long addr, unsigned long end, struct zap_details *details, int *rss, - bool *force_flush, bool *force_break) + bool *force_flush, bool *force_break, + bool *any_skipped) { pte_t ptent = ptep_get(pte); int max_nr = (end - addr) / PAGE_SIZE; @@ -1691,10 +1695,11 @@ static inline int do_zap_pte_range(struc if (pte_present(ptent)) nr += zap_present_ptes(tlb, vma, pte, ptent, max_nr, addr, - details, rss, force_flush, force_break); + details, rss, force_flush, force_break, + any_skipped); else nr += zap_nonpresent_ptes(tlb, vma, pte, ptent, max_nr, addr, - details, rss); + details, rss, any_skipped); return nr; } @@ -1705,6 +1710,7 @@ static unsigned long zap_pte_range(struc struct zap_details *details) { bool force_flush = false, force_break = false; + bool any_skipped = false; struct mm_struct *mm = tlb->mm; int rss[NR_MM_COUNTERS]; spinlock_t *ptl; @@ -1725,7 +1731,7 @@ static unsigned long zap_pte_range(struc break; nr = do_zap_pte_range(tlb, vma, pte, addr, end, details, rss, - &force_flush, &force_break); + &force_flush, &force_break, &any_skipped); if (unlikely(force_break)) { addr += nr * PAGE_SIZE; break; _ Patches currently in -mm which might be from zhengqi.arch@xxxxxxxxxxxxx are mm-pgtable-make-ptep_clear-non-atomic.patch mm-khugepaged-recheck-pmd-state-in-retract_page_tables.patch mm-userfaultfd-recheck-dst_pmd-entry-in-move_pages_pte.patch mm-introduce-zap_nonpresent_ptes.patch mm-introduce-do_zap_pte_range.patch mm-skip-over-all-consecutive-none-ptes-in-do_zap_pte_range.patch mm-zap_install_uffd_wp_if_needed-return-whether-uffd-wp-pte-has-been-re-installed.patch mm-do_zap_pte_range-return-any_skipped-information-to-the-caller.patch mm-make-zap_pte_range-handle-full-within-pmd-range.patch mm-pgtable-reclaim-empty-pte-page-in-madvisemadv_dontneed.patch x86-mm-free-page-table-pages-by-rcu-instead-of-semi-rcu.patch x86-select-arch_supports_pt_reclaim-if-x86_64.patch