diff options
Diffstat (limited to 'include/linux/mm_inline.h')
-rw-r--r-- | include/linux/mm_inline.h | 588 |
1 files changed, 521 insertions, 67 deletions
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 6f2fef7b0784..e8ed225d8f7c 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -2,33 +2,47 @@ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H +#include <linux/atomic.h> #include <linux/huge_mm.h> #include <linux/swap.h> +#include <linux/string.h> +#include <linux/userfaultfd_k.h> +#include <linux/swapops.h> /** - * page_is_file_cache - should the page be on a file LRU or anon LRU? - * @page: the page to test - * - * Returns 1 if @page is page cache page backed by a regular filesystem, - * or 0 if @page is anonymous, tmpfs or otherwise ram or swap backed. - * Used by functions that manipulate the LRU lists, to sort a page - * onto the right LRU list. + * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? + * @folio: The folio to test. * * We would like to get this info without a page flag, but the state - * needs to survive until the page is last deleted from the LRU, which + * needs to survive until the folio is last deleted from the LRU, which * could be as far down as __page_cache_release. + * + * Return: An integer (not a boolean!) used to sort a folio onto the + * right LRU list and to account folios correctly. + * 1 if @folio is a regular filesystem backed page cache folio + * or a lazily freed anonymous folio (e.g. via MADV_FREE). + * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise + * ram or swap backed folio. */ -static inline int page_is_file_cache(struct page *page) +static inline int folio_is_file_lru(struct folio *folio) +{ + return !folio_test_swapbacked(folio); +} + +static inline int page_is_file_lru(struct page *page) { - return !PageSwapBacked(page); + return folio_is_file_lru(page_folio(page)); } static __always_inline void __update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, - int nr_pages) + long nr_pages) { struct pglist_data *pgdat = lruvec_pgdat(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_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); @@ -36,7 +50,7 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec, static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, - int nr_pages) + long nr_pages) { __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG @@ -44,84 +58,524 @@ static __always_inline void update_lru_size(struct lruvec *lruvec, #endif } +/** + * __folio_clear_lru_flags - Clear page lru flags before releasing a page. + * @folio: The folio that was on lru and now has a zero reference. + */ +static __always_inline void __folio_clear_lru_flags(struct folio *folio) +{ + VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio); + + __folio_clear_lru(folio); + + /* this shouldn't happen, so leave the flags to bad_page() */ + if (folio_test_active(folio) && folio_test_unevictable(folio)) + return; + + __folio_clear_active(folio); + __folio_clear_unevictable(folio); +} + +/** + * folio_lru_list - Which LRU list should a folio be on? + * @folio: The folio to test. + * + * 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) +{ + enum lru_list lru; + + VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); + + if (folio_test_unevictable(folio)) + return LRU_UNEVICTABLE; + + lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; + if (folio_test_active(folio)) + lru += LRU_ACTIVE; + + return lru; +} + +#ifdef CONFIG_LRU_GEN + +#ifdef CONFIG_LRU_GEN_ENABLED +static inline bool lru_gen_enabled(void) +{ + DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]); + + return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]); +} +#else +static inline bool lru_gen_enabled(void) +{ + DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]); + + return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]); +} +#endif + +static inline bool lru_gen_in_fault(void) +{ + return current->in_lru_fault; +} + +static inline int lru_gen_from_seq(unsigned long seq) +{ + return seq % MAX_NR_GENS; +} + +static inline int lru_hist_from_seq(unsigned long seq) +{ + return seq % NR_HIST_GENS; +} + +static inline int lru_tier_from_refs(int refs) +{ + VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); + + /* see the comment in folio_lru_refs() */ + return order_base_2(refs + 1); +} + +static inline int folio_lru_refs(struct folio *folio) +{ + unsigned long flags = READ_ONCE(folio->flags); + bool workingset = flags & BIT(PG_workingset); + + /* + * 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 ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset; +} + +static inline int folio_lru_gen(struct folio *folio) +{ + unsigned long flags = READ_ONCE(folio->flags); + + return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; +} + +static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen) +{ + unsigned long max_seq = lruvec->lrugen.max_seq; + + VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); + + /* see the comment on MIN_NR_GENS */ + return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1); +} + +static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *folio, + int old_gen, int new_gen) +{ + int type = folio_is_file_lru(folio); + int zone = folio_zonenum(folio); + int delta = folio_nr_pages(folio); + enum lru_list lru = type * LRU_INACTIVE_FILE; + struct lru_gen_struct *lrugen = &lruvec->lrugen; + + VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS); + VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS); + VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1); + + if (old_gen >= 0) + WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone], + lrugen->nr_pages[old_gen][type][zone] - delta); + if (new_gen >= 0) + WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone], + lrugen->nr_pages[new_gen][type][zone] + delta); + + /* addition */ + if (old_gen < 0) { + if (lru_gen_is_active(lruvec, new_gen)) + lru += LRU_ACTIVE; + __update_lru_size(lruvec, lru, zone, delta); + return; + } + + /* deletion */ + if (new_gen < 0) { + if (lru_gen_is_active(lruvec, old_gen)) + lru += LRU_ACTIVE; + __update_lru_size(lruvec, lru, zone, -delta); + return; + } + + /* promotion */ + if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) { + __update_lru_size(lruvec, lru, zone, -delta); + __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta); + } + + /* demotion requires isolation, e.g., lru_deactivate_fn() */ + VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); +} + +static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + unsigned long seq; + unsigned long flags; + int gen = folio_lru_gen(folio); + int type = folio_is_file_lru(folio); + int zone = folio_zonenum(folio); + struct lru_gen_struct *lrugen = &lruvec->lrugen; + + VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); + + if (folio_test_unevictable(folio) || !lrugen->enabled) + return false; + /* + * There are three common cases for this page: + * 1. If it's hot, e.g., freshly faulted in or previously hot and + * migrated, add it to the youngest generation. + * 2. If it's cold but can't be evicted immediately, i.e., an anon page + * not in swapcache or a dirty page pending writeback, add it to the + * second oldest generation. + * 3. Everything else (clean, cold) is added to the oldest generation. + */ + 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->min_seq[type] + 1; + else + seq = lrugen->min_seq[type]; + + 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); + + lru_gen_update_size(lruvec, folio, -1, gen); + /* for folio_rotate_reclaimable() */ + if (reclaiming) + list_add_tail(&folio->lru, &lrugen->lists[gen][type][zone]); + else + list_add(&folio->lru, &lrugen->lists[gen][type][zone]); + + return true; +} + +static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + unsigned long flags; + int gen = folio_lru_gen(folio); + + if (gen < 0) + return false; + + VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); + VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(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); + gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; + + lru_gen_update_size(lruvec, folio, gen, -1); + list_del(&folio->lru); + + return true; +} + +#else /* !CONFIG_LRU_GEN */ + +static inline bool lru_gen_enabled(void) +{ + return false; +} + +static inline bool lru_gen_in_fault(void) +{ + return false; +} + +static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + return false; +} + +static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + return false; +} + +#endif /* CONFIG_LRU_GEN */ + +static __always_inline +void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) +{ + enum lru_list lru = folio_lru_list(folio); + + if (lru_gen_add_folio(lruvec, folio, false)) + return; + + update_lru_size(lruvec, lru, folio_zonenum(folio), + folio_nr_pages(folio)); + if (lru != LRU_UNEVICTABLE) + list_add(&folio->lru, &lruvec->lists[lru]); +} + static __always_inline void add_page_to_lru_list(struct page *page, - struct lruvec *lruvec, enum lru_list lru) + struct lruvec *lruvec) { - update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page)); - list_add(&page->lru, &lruvec->lists[lru]); + lruvec_add_folio(lruvec, page_folio(page)); } -static __always_inline void add_page_to_lru_list_tail(struct page *page, - struct lruvec *lruvec, enum lru_list lru) +static __always_inline +void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) { - update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page)); - list_add_tail(&page->lru, &lruvec->lists[lru]); + enum lru_list lru = folio_lru_list(folio); + + if (lru_gen_add_folio(lruvec, folio, true)) + return; + + update_lru_size(lruvec, lru, folio_zonenum(folio), + folio_nr_pages(folio)); + /* This is not expected to be used on LRU_UNEVICTABLE */ + list_add_tail(&folio->lru, &lruvec->lists[lru]); +} + +static __always_inline +void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) +{ + enum lru_list lru = folio_lru_list(folio); + + if (lru_gen_del_folio(lruvec, folio, false)) + return; + + if (lru != LRU_UNEVICTABLE) + list_del(&folio->lru); + update_lru_size(lruvec, lru, folio_zonenum(folio), + -folio_nr_pages(folio)); } static __always_inline void del_page_from_lru_list(struct page *page, - struct lruvec *lruvec, enum lru_list lru) + struct lruvec *lruvec) { - list_del(&page->lru); - update_lru_size(lruvec, lru, page_zonenum(page), -hpage_nr_pages(page)); + lruvec_del_folio(lruvec, page_folio(page)); } -/** - * page_lru_base_type - which LRU list type should a page be on? - * @page: the page to test - * - * Used for LRU list index arithmetic. - * - * Returns the base LRU type - file or anon - @page should be on. +#ifdef CONFIG_ANON_VMA_NAME +/* + * mmap_lock should be read-locked when calling anon_vma_name(). Caller should + * either keep holding the lock while using the returned pointer or it should + * raise anon_vma_name refcount before releasing the lock. */ -static inline enum lru_list page_lru_base_type(struct page *page) +extern struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma); +extern struct anon_vma_name *anon_vma_name_alloc(const char *name); +extern void anon_vma_name_free(struct kref *kref); + +/* mmap_lock should be read-locked */ +static inline void anon_vma_name_get(struct anon_vma_name *anon_name) { - if (page_is_file_cache(page)) - return LRU_INACTIVE_FILE; - return LRU_INACTIVE_ANON; + if (anon_name) + kref_get(&anon_name->kref); } -/** - * page_off_lru - which LRU list was page on? clearing its lru flags. - * @page: the page to test - * - * Returns the LRU list a page was on, as an index into the array of LRU - * lists; and clears its Unevictable or Active flags, ready for freeing. - */ -static __always_inline enum lru_list page_off_lru(struct page *page) +static inline void anon_vma_name_put(struct anon_vma_name *anon_name) { - enum lru_list lru; + if (anon_name) + kref_put(&anon_name->kref, anon_vma_name_free); +} + +static inline +struct anon_vma_name *anon_vma_name_reuse(struct anon_vma_name *anon_name) +{ + /* Prevent anon_name refcount saturation early on */ + if (kref_read(&anon_name->kref) < REFCOUNT_MAX) { + anon_vma_name_get(anon_name); + return anon_name; - if (PageUnevictable(page)) { - __ClearPageUnevictable(page); - lru = LRU_UNEVICTABLE; - } else { - lru = page_lru_base_type(page); - if (PageActive(page)) { - __ClearPageActive(page); - lru += LRU_ACTIVE; - } } - return lru; + return anon_vma_name_alloc(anon_name->name); } -/** - * page_lru - which LRU list should a page be on? - * @page: the page to test +static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) +{ + struct anon_vma_name *anon_name = anon_vma_name(orig_vma); + + if (anon_name) + new_vma->anon_name = anon_vma_name_reuse(anon_name); +} + +static inline void free_anon_vma_name(struct vm_area_struct *vma) +{ + /* + * Not using anon_vma_name because it generates a warning if mmap_lock + * is not held, which might be the case here. + */ + if (!vma->vm_file) + anon_vma_name_put(vma->anon_name); +} + +static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, + struct anon_vma_name *anon_name2) +{ + if (anon_name1 == anon_name2) + return true; + + return anon_name1 && anon_name2 && + !strcmp(anon_name1->name, anon_name2->name); +} + +#else /* CONFIG_ANON_VMA_NAME */ +static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) +{ + return NULL; +} + +static inline struct anon_vma_name *anon_vma_name_alloc(const char *name) +{ + return NULL; +} + +static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {} +static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {} +static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) {} +static inline void free_anon_vma_name(struct vm_area_struct *vma) {} + +static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, + struct anon_vma_name *anon_name2) +{ + return true; +} + +#endif /* CONFIG_ANON_VMA_NAME */ + +static inline void init_tlb_flush_pending(struct mm_struct *mm) +{ + atomic_set(&mm->tlb_flush_pending, 0); +} + +static inline void inc_tlb_flush_pending(struct mm_struct *mm) +{ + atomic_inc(&mm->tlb_flush_pending); + /* + * The only time this value is relevant is when there are indeed pages + * to flush. And we'll only flush pages after changing them, which + * requires the PTL. + * + * So the ordering here is: + * + * atomic_inc(&mm->tlb_flush_pending); + * spin_lock(&ptl); + * ... + * set_pte_at(); + * spin_unlock(&ptl); + * + * spin_lock(&ptl) + * mm_tlb_flush_pending(); + * .... + * spin_unlock(&ptl); + * + * flush_tlb_range(); + * atomic_dec(&mm->tlb_flush_pending); + * + * Where the increment if constrained by the PTL unlock, it thus + * ensures that the increment is visible if the PTE modification is + * visible. After all, if there is no PTE modification, nobody cares + * about TLB flushes either. + * + * This very much relies on users (mm_tlb_flush_pending() and + * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and + * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc + * locks (PPC) the unlock of one doesn't order against the lock of + * another PTL. + * + * The decrement is ordered by the flush_tlb_range(), such that + * mm_tlb_flush_pending() will not return false unless all flushes have + * completed. + */ +} + +static inline void dec_tlb_flush_pending(struct mm_struct *mm) +{ + /* + * See inc_tlb_flush_pending(). + * + * This cannot be smp_mb__before_atomic() because smp_mb() simply does + * not order against TLB invalidate completion, which is what we need. + * + * Therefore we must rely on tlb_flush_*() to guarantee order. + */ + atomic_dec(&mm->tlb_flush_pending); +} + +static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +{ + /* + * Must be called after having acquired the PTL; orders against that + * PTLs release and therefore ensures that if we observe the modified + * PTE we must also observe the increment from inc_tlb_flush_pending(). + * + * That is, it only guarantees to return true if there is a flush + * pending for _this_ PTL. + */ + return atomic_read(&mm->tlb_flush_pending); +} + +static inline bool mm_tlb_flush_nested(struct mm_struct *mm) +{ + /* + * Similar to mm_tlb_flush_pending(), we must have acquired the PTL + * for which there is a TLB flush pending in order to guarantee + * we've seen both that PTE modification and the increment. + * + * (no requirement on actually still holding the PTL, that is irrelevant) + */ + return atomic_read(&mm->tlb_flush_pending) > 1; +} + +/* + * 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. * - * Returns the LRU list a page should be on, as an index - * into the array of LRU lists. + * 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. */ -static __always_inline enum lru_list page_lru(struct page *page) +static inline void +pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, + pte_t *pte, pte_t pteval) { - enum lru_list lru; +#ifdef CONFIG_PTE_MARKER_UFFD_WP + bool arm_uffd_pte = false; - if (PageUnevictable(page)) - lru = LRU_UNEVICTABLE; - else { - lru = page_lru_base_type(page); - if (PageActive(page)) - lru += LRU_ACTIVE; - } - return lru; + /* The current status of the pte should be "cleared" before calling */ + WARN_ON_ONCE(!pte_none(*pte)); + + if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) + return; + + /* A uffd-wp wr-protected normal pte */ + if (unlikely(pte_present(pteval) && pte_uffd_wp(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_wp_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)); +#endif } + #endif |