pte_install_uffd_wp_if_needed() has grown too large for mm_inline.h. Move it to memory.c. This helper is only used inside mm/, so declare it in mm/internal.h instead of a public header. While at it, convert the comment to kerneldoc and rename the local arguments from pte/pteval to ptep/pte so the pointer and PTE value are easier to distinguish. Signed-off-by: Dev Jain --- include/linux/mm_inline.h | 53 ---------------------------------- mm/internal.h | 3 ++ mm/memory.c | 60 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 63 insertions(+), 53 deletions(-) diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index b5c4dc0f3fe32..621c8653d8f7e 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -566,59 +566,6 @@ static inline pte_marker copy_pte_marker( return dstm; } -/* - * If this pte is wr-protected by uffd-wp in any form, arm the special pte to - * replace a none pte. NOTE! This should only be called when *pte is already - * cleared so we will never accidentally replace something valuable. Meanwhile - * none pte also means we are not demoting the pte so tlb flushed is not needed. - * E.g., when pte cleared the caller should have taken care of the tlb flush. - * - * Must be called with pgtable lock held so that no thread will see the none - * pte, and if they see it, they'll fault and serialize at the pgtable lock. - * - * Returns true if an uffd-wp pte was installed, false otherwise. - */ -static inline bool -pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, - pte_t *pte, pte_t pteval) -{ - bool arm_uffd_pte = false; - - if (!uffd_supports_wp_marker()) - return false; - - /* The current status of the pte should be "cleared" before calling */ - WARN_ON_ONCE(!pte_none(ptep_get(pte))); - - /* - * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole - * thing, because when zapping either it means it's dropping the - * page, or in TTU where the present pte will be quickly replaced - * with a swap pte. There's no way of leaking the bit. - */ - if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) - return false; - - /* A uffd-wp wr-protected normal pte */ - if (unlikely(pte_present(pteval) && pte_uffd(pteval))) - arm_uffd_pte = true; - - /* - * A uffd-wp wr-protected swap pte. Note: this should even cover an - * existing pte marker with uffd-wp bit set. - */ - if (unlikely(pte_swp_uffd_any(pteval))) - arm_uffd_pte = true; - - if (unlikely(arm_uffd_pte)) { - set_pte_at(vma->vm_mm, addr, pte, - make_pte_marker(PTE_MARKER_UFFD_WP)); - return true; - } - - return false; -} - static inline bool vma_has_recency(const struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)) diff --git a/mm/internal.h b/mm/internal.h index f26423de4ca28..b6a3589a61c1a 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -276,6 +276,9 @@ void unmap_vmas(struct mmu_gather *tlb, struct unmap_desc *unmap); #ifdef CONFIG_MMU +bool pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, pte_t pte); + static inline void get_anon_vma(struct anon_vma *anon_vma) { atomic_inc(&anon_vma->refcount); diff --git a/mm/memory.c b/mm/memory.c index d5e87624f6920..6c0c4c774674a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1675,6 +1675,66 @@ static inline bool zap_drop_markers(struct zap_details *details) return details->zap_flags & ZAP_FLAG_DROP_MARKER; } +/** + * pte_install_uffd_wp_if_needed - install uffd-wp marker after clearing a PTE + * @vma: The VMA the page is mapped into. + * @addr: Address the page is mapped at. + * @ptep: Page table pointer for this entry. + * @pte: Old value of the entry pointed to by @ptep. + * + * If the PTE was write-protected by uffd-wp in any form, arm a special PTE + * to replace a none PTE. NOTE! This should only be called when the PTE is + * already cleared so we will never accidentally replace something valuable. + * Meanwhile none PTEs also mean we are not demoting the PTE so a TLB flush is + * not needed. E.g., when the PTE was cleared, the caller should have taken care + * of the TLB flush. + * + * Must be called with the page table lock held so that no thread will see the + * none PTE, and if they see it, they'll fault and serialize at the page table + * lock. + * + * Returns true if an uffd-wp PTE was installed, false otherwise. + */ +bool pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, pte_t pte) +{ + bool arm_uffd_pte = false; + + if (!uffd_supports_wp_marker()) + return false; + + /* The current status of the pte should be "cleared" before calling */ + WARN_ON_ONCE(!pte_none(ptep_get(ptep))); + + /* + * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole + * thing, because when zapping either it means it's dropping the + * page, or in TTU where the present pte will be quickly replaced + * with a swap pte. There's no way of leaking the bit. + */ + if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) + return false; + + /* A uffd-wp wr-protected normal pte */ + if (unlikely(pte_present(pte) && pte_uffd(pte))) + arm_uffd_pte = true; + + /* + * A uffd-wp wr-protected swap pte. Note: this should even cover an + * existing pte marker with uffd-wp bit set. + */ + if (unlikely(pte_swp_uffd_any(pte))) + arm_uffd_pte = true; + + if (unlikely(arm_uffd_pte)) { + set_pte_at(vma->vm_mm, addr, ptep, + make_pte_marker(PTE_MARKER_UFFD_WP)); + return true; + } + + return false; +} + /* * This function makes sure that we'll replace the none pte with an uffd-wp * swap special pte marker when necessary. Must be with the pgtable lock held. -- 2.43.0 Enable batch setting of uffd-wp PTE markers. The code paths passing nr > 1 to zap_install_uffd_wp_if_needed() produce that nr through either folio_pte_batch() or swap_pte_batch(), therefore batching is correct: 1) All PTEs belong to the same type of VMA: anonymous or non-anonymous, wp-armed or non-wp-armed. 2) All PTEs are either marked with uffd-wp or not marked with uffd-wp; the same applies to the pte_swp_uffd_any() check. 3) uffd_supports_wp_marker() is independent of the function parameters. Use set_pte_at() in a loop instead of set_ptes(), because set_ptes() cannot handle nonpresent to nonpresent conversion for nr_pages > 1. Rename the helper to cond_install_uffd_wp_ptes(). Signed-off-by: Dev Jain --- mm/internal.h | 5 +++-- mm/memory.c | 61 +++++++++++++++++++++------------------------------ mm/rmap.c | 2 +- 3 files changed, 29 insertions(+), 39 deletions(-) diff --git a/mm/internal.h b/mm/internal.h index b6a3589a61c1a..0f49cff67a2b8 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -276,8 +276,9 @@ void unmap_vmas(struct mmu_gather *tlb, struct unmap_desc *unmap); #ifdef CONFIG_MMU -bool pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, pte_t pte); +bool cond_install_uffd_wp_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, pte_t pte, + unsigned long nr_ptes); static inline void get_anon_vma(struct anon_vma *anon_vma) { diff --git a/mm/memory.c b/mm/memory.c index 6c0c4c774674a..d2f14ba2261cd 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1676,27 +1676,29 @@ static inline bool zap_drop_markers(struct zap_details *details) } /** - * pte_install_uffd_wp_if_needed - install uffd-wp marker after clearing a PTE - * @vma: The VMA the page is mapped into. - * @addr: Address the page is mapped at. - * @ptep: Page table pointer for this entry. + * cond_install_uffd_wp_ptes - install uffd-wp markers after clearing PTEs + * @vma: The VMA the pages are mapped into. + * @addr: Address the first page of this batch is mapped at. + * @ptep: Page table pointer for the first entry of this batch. * @pte: Old value of the entry pointed to by @ptep. + * @nr_ptes: Number of entries to install. * - * If the PTE was write-protected by uffd-wp in any form, arm a special PTE - * to replace a none PTE. NOTE! This should only be called when the PTE is + * If the PTEs were write-protected by uffd-wp in any form, arm special PTEs + * to replace none PTEs. NOTE! This should only be called when the PTEs are * already cleared so we will never accidentally replace something valuable. - * Meanwhile none PTEs also mean we are not demoting the PTE so a TLB flush is - * not needed. E.g., when the PTE was cleared, the caller should have taken care - * of the TLB flush. + * Meanwhile none PTEs also mean we are not demoting the PTEs so a TLB flush is + * not needed. E.g., when the PTEs were cleared, the caller should have taken + * care of the TLB flush. * * Must be called with the page table lock held so that no thread will see the - * none PTE, and if they see it, they'll fault and serialize at the page table + * none PTEs, and if they see them, they'll fault and serialize at the page table * lock. * - * Returns true if an uffd-wp PTE was installed, false otherwise. + * Returns true if uffd-wp PTEs were installed, false otherwise. */ -bool pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, pte_t pte) +bool cond_install_uffd_wp_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, pte_t pte, + unsigned long nr_ptes) { bool arm_uffd_pte = false; @@ -1726,13 +1728,19 @@ bool pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, if (unlikely(pte_swp_uffd_any(pte))) arm_uffd_pte = true; - if (unlikely(arm_uffd_pte)) { + if (likely(!arm_uffd_pte)) + return false; + + for (;;) { set_pte_at(vma->vm_mm, addr, ptep, make_pte_marker(PTE_MARKER_UFFD_WP)); - return true; + if (--nr_ptes == 0) + break; + ptep++; + addr += PAGE_SIZE; } - return false; + return true; } /* @@ -1746,29 +1754,10 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, int nr, struct zap_details *details, pte_t pteval) { - bool was_installed = false; - - if (!uffd_supports_wp_marker()) - return false; - - /* Zap on anonymous always means dropping everything */ - if (vma_is_anonymous(vma)) - return false; - if (zap_drop_markers(details)) return false; - for (;;) { - /* the PFN in the PTE is irrelevant. */ - if (pte_install_uffd_wp_if_needed(vma, addr, pte, pteval)) - was_installed = true; - if (--nr == 0) - break; - pte++; - addr += PAGE_SIZE; - } - - return was_installed; + return cond_install_uffd_wp_ptes(vma, addr, pte, pteval, nr); } static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb, diff --git a/mm/rmap.c b/mm/rmap.c index 73c2fe2d19462..abeb8e7ceba17 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -2348,7 +2348,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, * we may want to replace a none pte with a marker pte if * it's file-backed, so we don't lose the tracking info. */ - pte_install_uffd_wp_if_needed(vma, address, pvmw.pte, pteval); + cond_install_uffd_wp_ptes(vma, address, pvmw.pte, pteval, 1); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); -- 2.43.0 Commit a67fe41e214f ("mm: rmap: support batched unmapping for file large folios") extended batched unmapping for file folios. That also required making pte_install_uffd_wp_if_needed() support batching, but that was left out for the time being. Correctness was maintained by stopping batching if the VMA the folio belongs to is marked uffd-wp. Now that cond_install_uffd_wp_ptes() supports batching, call it with the full batch length and allow folio_unmap_pte_batch() to batch file folios belonging to uffd-wp VMAs. For file folios, if the uffd-wp bit is set, unmapping converts present PTEs into uffd-wp markers. We must ensure that the same PTE range is not reprocessed by the try_to_unmap_one() loop. The page_vma_mapped_walk API ensures this: check_pte() only returns true if any PFN in [pvmw->pfn, pvmw->pfn + nr_pages) is mapped by the PTE. There is no PFN underlying a uffd-wp marker PTE, so check_pte() returns false and the walk skips ahead until it reaches a present entry again. Acked-by: David Hildenbrand (Arm) Signed-off-by: Dev Jain --- mm/rmap.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/mm/rmap.c b/mm/rmap.c index abeb8e7ceba17..56eaddfc610b1 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1968,9 +1968,6 @@ static inline unsigned int folio_unmap_pte_batch(struct folio *folio, if (pte_unused(pte)) return 1; - if (userfaultfd_protected(vma)) - return 1; - /* * If unmap fails, we need to restore the ptes. To avoid accidentally * upgrading write permissions for ptes that were not originally @@ -2348,7 +2345,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, * we may want to replace a none pte with a marker pte if * it's file-backed, so we don't lose the tracking info. */ - cond_install_uffd_wp_ptes(vma, address, pvmw.pte, pteval, 1); + cond_install_uffd_wp_ptes(vma, address, pvmw.pte, pteval, + nr_pages); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); -- 2.43.0