diff options
Diffstat (limited to 'include/linux/mm_inline.h')
| -rw-r--r-- | include/linux/mm_inline.h | 175 |
1 files changed, 120 insertions, 55 deletions
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index f4fe593c1400..fa2d6ba811b5 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -8,7 +8,7 @@ #include <linux/swap.h> #include <linux/string.h> #include <linux/userfaultfd_k.h> -#include <linux/swapops.h> +#include <linux/leafops.h> /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? @@ -25,7 +25,7 @@ * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise * ram or swap backed folio. */ -static inline int folio_is_file_lru(struct folio *folio) +static inline int folio_is_file_lru(const struct folio *folio) { return !folio_test_swapbacked(folio); } @@ -44,7 +44,7 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec, lockdep_assert_held(&lruvec->lru_lock); WARN_ON_ONCE(nr_pages != (int)nr_pages); - __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); + mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); } @@ -84,7 +84,7 @@ static __always_inline void __folio_clear_lru_flags(struct folio *folio) * Return: The LRU list a folio should be on, as an index * into the array of LRU lists. */ -static __always_inline enum lru_list folio_lru_list(struct folio *folio) +static __always_inline enum lru_list folio_lru_list(const struct folio *folio) { enum lru_list lru; @@ -133,36 +133,35 @@ static inline int lru_hist_from_seq(unsigned long seq) return seq % NR_HIST_GENS; } -static inline int lru_tier_from_refs(int refs) +static inline int lru_tier_from_refs(int refs, bool workingset) { VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); - /* see the comment in folio_lru_refs() */ - return order_base_2(refs + 1); + /* see the comment on MAX_NR_TIERS */ + return workingset ? MAX_NR_TIERS - 1 : order_base_2(refs); } -static inline int folio_lru_refs(struct folio *folio) +static inline int folio_lru_refs(const struct folio *folio) { - unsigned long flags = READ_ONCE(folio->flags); - bool workingset = flags & BIT(PG_workingset); + unsigned long flags = READ_ONCE(folio->flags.f); + if (!(flags & BIT(PG_referenced))) + return 0; /* - * Return the number of accesses beyond PG_referenced, i.e., N-1 if the - * total number of accesses is N>1, since N=0,1 both map to the first - * tier. lru_tier_from_refs() will account for this off-by-one. Also see - * the comment on MAX_NR_TIERS. + * Return the total number of accesses including PG_referenced. Also see + * the comment on LRU_REFS_FLAGS. */ - return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset; + return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + 1; } -static inline int folio_lru_gen(struct folio *folio) +static inline int folio_lru_gen(const struct folio *folio) { - unsigned long flags = READ_ONCE(folio->flags); + unsigned long flags = READ_ONCE(folio->flags.f); return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } -static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen) +static inline bool lru_gen_is_active(const struct lruvec *lruvec, int gen) { unsigned long max_seq = lruvec->lrugen.max_seq; @@ -218,6 +217,40 @@ static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *foli VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); } +static inline unsigned long lru_gen_folio_seq(const struct lruvec *lruvec, + const struct folio *folio, + bool reclaiming) +{ + int gen; + int type = folio_is_file_lru(folio); + const struct lru_gen_folio *lrugen = &lruvec->lrugen; + + /* + * +-----------------------------------+-----------------------------------+ + * | Accessed through page tables and | Accessed through file descriptors | + * | promoted by folio_update_gen() | and protected by folio_inc_gen() | + * +-----------------------------------+-----------------------------------+ + * | PG_active (set while isolated) | | + * +-----------------+-----------------+-----------------+-----------------+ + * | PG_workingset | PG_referenced | PG_workingset | LRU_REFS_FLAGS | + * +-----------------------------------+-----------------------------------+ + * |<---------- MIN_NR_GENS ---------->| | + * |<---------------------------- MAX_NR_GENS ---------------------------->| + */ + if (folio_test_active(folio)) + gen = MIN_NR_GENS - folio_test_workingset(folio); + else if (reclaiming) + gen = MAX_NR_GENS; + else if ((!folio_is_file_lru(folio) && !folio_test_swapcache(folio)) || + (folio_test_reclaim(folio) && + (folio_test_dirty(folio) || folio_test_writeback(folio)))) + gen = MIN_NR_GENS; + else + gen = MAX_NR_GENS - folio_test_workingset(folio); + + return max(READ_ONCE(lrugen->max_seq) - gen + 1, READ_ONCE(lrugen->min_seq[type])); +} + static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long seq; @@ -231,33 +264,12 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, if (folio_test_unevictable(folio) || !lrugen->enabled) return false; - /* - * There are four common cases for this page: - * 1. If it's hot, i.e., freshly faulted in, add it to the youngest - * generation, and it's protected over the rest below. - * 2. If it can't be evicted immediately, i.e., a dirty page pending - * writeback, add it to the second youngest generation. - * 3. If it should be evicted first, e.g., cold and clean from - * folio_rotate_reclaimable(), add it to the oldest generation. - * 4. Everything else falls between 2 & 3 above and is added to the - * second oldest generation if it's considered inactive, or the - * oldest generation otherwise. See lru_gen_is_active(). - */ - if (folio_test_active(folio)) - seq = lrugen->max_seq; - else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) || - (folio_test_reclaim(folio) && - (folio_test_dirty(folio) || folio_test_writeback(folio)))) - seq = lrugen->max_seq - 1; - else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq) - seq = lrugen->min_seq[type]; - else - seq = lrugen->min_seq[type] + 1; + seq = lru_gen_folio_seq(lruvec, folio, reclaiming); gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ - set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags); + set_mask_bits(&folio->flags.f, LRU_GEN_MASK | BIT(PG_active), flags); lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ @@ -282,7 +294,7 @@ static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, /* for folio_migrate_flags() */ flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0; - flags = set_mask_bits(&folio->flags, LRU_GEN_MASK, flags); + flags = set_mask_bits(&folio->flags.f, LRU_GEN_MASK, flags); gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; lru_gen_update_size(lruvec, folio, gen, -1); @@ -291,6 +303,12 @@ static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, return true; } +static inline void folio_migrate_refs(struct folio *new, const struct folio *old) +{ + unsigned long refs = READ_ONCE(old->flags.f) & LRU_REFS_MASK; + + set_mask_bits(&new->flags.f, LRU_REFS_MASK, refs); +} #else /* !CONFIG_LRU_GEN */ static inline bool lru_gen_enabled(void) @@ -313,6 +331,10 @@ static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, return false; } +static inline void folio_migrate_refs(struct folio *new, const struct folio *old) +{ + +} #endif /* CONFIG_LRU_GEN */ static __always_inline @@ -426,6 +448,8 @@ static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, #endif /* CONFIG_ANON_VMA_NAME */ +void pfnmap_track_ctx_release(struct kref *ref); + static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); @@ -485,7 +509,7 @@ static inline void dec_tlb_flush_pending(struct mm_struct *mm) atomic_dec(&mm->tlb_flush_pending); } -static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +static inline bool mm_tlb_flush_pending(const struct mm_struct *mm) { /* * Must be called after having acquired the PTL; orders against that @@ -498,7 +522,7 @@ static inline bool mm_tlb_flush_pending(struct mm_struct *mm) return atomic_read(&mm->tlb_flush_pending); } -static inline bool mm_tlb_flush_nested(struct mm_struct *mm) +static inline bool mm_tlb_flush_nested(const struct mm_struct *mm) { /* * Similar to mm_tlb_flush_pending(), we must have acquired the PTL @@ -517,11 +541,11 @@ static inline bool mm_tlb_flush_nested(struct mm_struct *mm) * The caller should insert a new pte created with make_pte_marker(). */ static inline pte_marker copy_pte_marker( - swp_entry_t entry, struct vm_area_struct *dst_vma) + softleaf_t entry, struct vm_area_struct *dst_vma) { - pte_marker srcm = pte_marker_get(entry); + const pte_marker srcm = softleaf_to_marker(entry); /* Always copy error entries. */ - pte_marker dstm = srcm & PTE_MARKER_POISONED; + pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD); /* Only copy PTE markers if UFFD register matches. */ if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma)) @@ -529,7 +553,6 @@ static inline pte_marker copy_pte_marker( return dstm; } -#endif /* * If this pte is wr-protected by uffd-wp in any form, arm the special pte to @@ -541,15 +564,17 @@ static inline pte_marker copy_pte_marker( * 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. * - * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled. + * Returns true if an uffd-wp pte was installed, false otherwise. */ -static inline void +static inline bool pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, pte_t pteval) { -#ifdef CONFIG_PTE_MARKER_UFFD_WP 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))); @@ -560,7 +585,7 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, * with a swap pte. There's no way of leaking the bit. */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) - return; + return false; /* A uffd-wp wr-protected normal pte */ if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) @@ -573,13 +598,16 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, if (unlikely(pte_swp_uffd_wp_any(pteval))) arm_uffd_pte = true; - if (unlikely(arm_uffd_pte)) + if (unlikely(arm_uffd_pte)) { set_pte_at(vma->vm_mm, addr, pte, make_pte_marker(PTE_MARKER_UFFD_WP)); -#endif + return true; + } + + return false; } -static inline bool vma_has_recency(struct vm_area_struct *vma) +static inline bool vma_has_recency(const struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)) return false; @@ -589,5 +617,42 @@ static inline bool vma_has_recency(struct vm_area_struct *vma) return true; } +#endif + +/** + * num_pages_contiguous() - determine the number of contiguous pages + * that represent contiguous PFNs + * @pages: an array of page pointers + * @nr_pages: length of the array, at least 1 + * + * Determine the number of contiguous pages that represent contiguous PFNs + * in @pages, starting from the first page. + * + * In some kernel configs contiguous PFNs will not have contiguous struct + * pages. In these configurations num_pages_contiguous() will return a num + * smaller than ideal number. The caller should continue to check for pfn + * contiguity after each call to num_pages_contiguous(). + * + * Returns the number of contiguous pages. + */ +static inline size_t num_pages_contiguous(struct page **pages, size_t nr_pages) +{ + struct page *cur_page = pages[0]; + unsigned long section = memdesc_section(cur_page->flags); + size_t i; + + for (i = 1; i < nr_pages; i++) { + if (++cur_page != pages[i]) + break; + /* + * In unproblematic kernel configs, page_to_section() == 0 and + * the whole check will get optimized out. + */ + if (memdesc_section(cur_page->flags) != section) + break; + } + + return i; +} #endif |