diff options
Diffstat (limited to 'mm/swap.c')
| -rw-r--r-- | mm/swap.c | 1464 |
1 files changed, 834 insertions, 630 deletions
diff --git a/mm/swap.c b/mm/swap.c index 4a1d0d2c52fa..2260dcd2775e 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swap.c * @@ -7,7 +8,7 @@ /* * This file contains the default values for the operation of the * Linux VM subsystem. Fine-tuning documentation can be found in - * Documentation/sysctl/vm.txt. + * Documentation/admin-guide/sysctl/vm.rst. * Started 18.12.91 * Swap aging added 23.2.95, Stephen Tweedie. * Buffermem limits added 12.3.98, Rik van Riel. @@ -24,6 +25,7 @@ #include <linux/export.h> #include <linux/mm_inline.h> #include <linux/percpu_counter.h> +#include <linux/memremap.h> #include <linux/percpu.h> #include <linux/cpu.h> #include <linux/notifier.h> @@ -31,875 +33,1075 @@ #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> +#include <linux/hugetlb.h> +#include <linux/page_idle.h> +#include <linux/local_lock.h> +#include <linux/buffer_head.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/pagemap.h> -/* How many pages do we try to swap or page in/out together? */ +/* How many pages do we try to swap or page in/out together? As a power of 2 */ int page_cluster; +static const int page_cluster_max = 31; -static DEFINE_PER_CPU(struct pagevec, lru_add_pvec); -static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); -static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs); - -/* - * This path almost never happens for VM activity - pages are normally - * freed via pagevecs. But it gets used by networking. - */ -static void __page_cache_release(struct page *page) +struct cpu_fbatches { + /* + * The following folio batches are grouped together because they are protected + * by disabling preemption (and interrupts remain enabled). + */ + local_lock_t lock; + struct folio_batch lru_add; + struct folio_batch lru_deactivate_file; + struct folio_batch lru_deactivate; + struct folio_batch lru_lazyfree; +#ifdef CONFIG_SMP + struct folio_batch lru_activate; +#endif + /* Protecting the following batches which require disabling interrupts */ + local_lock_t lock_irq; + struct folio_batch lru_move_tail; +}; + +static DEFINE_PER_CPU(struct cpu_fbatches, cpu_fbatches) = { + .lock = INIT_LOCAL_LOCK(lock), + .lock_irq = INIT_LOCAL_LOCK(lock_irq), +}; + +static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp, + unsigned long *flagsp) { - if (PageLRU(page)) { - struct zone *zone = page_zone(page); - struct lruvec *lruvec; - unsigned long flags; - - spin_lock_irqsave(&zone->lru_lock, flags); - lruvec = mem_cgroup_page_lruvec(page, zone); - VM_BUG_ON(!PageLRU(page)); - __ClearPageLRU(page); - del_page_from_lru_list(page, lruvec, page_off_lru(page)); - spin_unlock_irqrestore(&zone->lru_lock, flags); + if (folio_test_lru(folio)) { + folio_lruvec_relock_irqsave(folio, lruvecp, flagsp); + lruvec_del_folio(*lruvecp, folio); + __folio_clear_lru_flags(folio); } } -static void __put_single_page(struct page *page) -{ - __page_cache_release(page); - free_hot_cold_page(page, 0); -} - -static void __put_compound_page(struct page *page) +/* + * This path almost never happens for VM activity - pages are normally freed + * in batches. But it gets used by networking - and for compound pages. + */ +static void page_cache_release(struct folio *folio) { - compound_page_dtor *dtor; + struct lruvec *lruvec = NULL; + unsigned long flags; - __page_cache_release(page); - dtor = get_compound_page_dtor(page); - (*dtor)(page); + __page_cache_release(folio, &lruvec, &flags); + if (lruvec) + unlock_page_lruvec_irqrestore(lruvec, flags); } -static void put_compound_page(struct page *page) +void __folio_put(struct folio *folio) { - if (unlikely(PageTail(page))) { - /* __split_huge_page_refcount can run under us */ - struct page *page_head = compound_trans_head(page); - - if (likely(page != page_head && - get_page_unless_zero(page_head))) { - unsigned long flags; - - /* - * THP can not break up slab pages so avoid taking - * compound_lock(). Slab performs non-atomic bit ops - * on page->flags for better performance. In particular - * slab_unlock() in slub used to be a hot path. It is - * still hot on arches that do not support - * this_cpu_cmpxchg_double(). - */ - if (PageSlab(page_head)) { - if (PageTail(page)) { - if (put_page_testzero(page_head)) - VM_BUG_ON(1); + if (unlikely(folio_is_zone_device(folio))) { + free_zone_device_folio(folio); + return; + } - atomic_dec(&page->_mapcount); - goto skip_lock_tail; - } else - goto skip_lock; - } - /* - * page_head wasn't a dangling pointer but it - * may not be a head page anymore by the time - * we obtain the lock. That is ok as long as it - * can't be freed from under us. - */ - flags = compound_lock_irqsave(page_head); - if (unlikely(!PageTail(page))) { - /* __split_huge_page_refcount run before us */ - compound_unlock_irqrestore(page_head, flags); -skip_lock: - if (put_page_testzero(page_head)) - __put_single_page(page_head); -out_put_single: - if (put_page_testzero(page)) - __put_single_page(page); - return; - } - VM_BUG_ON(page_head != page->first_page); - /* - * We can release the refcount taken by - * get_page_unless_zero() now that - * __split_huge_page_refcount() is blocked on - * the compound_lock. - */ - if (put_page_testzero(page_head)) - VM_BUG_ON(1); - /* __split_huge_page_refcount will wait now */ - VM_BUG_ON(page_mapcount(page) <= 0); - atomic_dec(&page->_mapcount); - VM_BUG_ON(atomic_read(&page_head->_count) <= 0); - VM_BUG_ON(atomic_read(&page->_count) != 0); - compound_unlock_irqrestore(page_head, flags); - -skip_lock_tail: - if (put_page_testzero(page_head)) { - if (PageHead(page_head)) - __put_compound_page(page_head); - else - __put_single_page(page_head); - } - } else { - /* page_head is a dangling pointer */ - VM_BUG_ON(PageTail(page)); - goto out_put_single; - } - } else if (put_page_testzero(page)) { - if (PageHead(page)) - __put_compound_page(page); - else - __put_single_page(page); + if (folio_test_hugetlb(folio)) { + free_huge_folio(folio); + return; } -} -void put_page(struct page *page) -{ - if (unlikely(PageCompound(page))) - put_compound_page(page); - else if (put_page_testzero(page)) - __put_single_page(page); + page_cache_release(folio); + folio_unqueue_deferred_split(folio); + mem_cgroup_uncharge(folio); + free_frozen_pages(&folio->page, folio_order(folio)); } -EXPORT_SYMBOL(put_page); +EXPORT_SYMBOL(__folio_put); -/* - * This function is exported but must not be called by anything other - * than get_page(). It implements the slow path of get_page(). - */ -bool __get_page_tail(struct page *page) +typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio); + +static void lru_add(struct lruvec *lruvec, struct folio *folio) { + int was_unevictable = folio_test_clear_unevictable(folio); + long nr_pages = folio_nr_pages(folio); + + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); + /* - * This takes care of get_page() if run on a tail page - * returned by one of the get_user_pages/follow_page variants. - * get_user_pages/follow_page itself doesn't need the compound - * lock because it runs __get_page_tail_foll() under the - * proper PT lock that already serializes against - * split_huge_page(). + * Is an smp_mb__after_atomic() still required here, before + * folio_evictable() tests the mlocked flag, to rule out the possibility + * of stranding an evictable folio on an unevictable LRU? I think + * not, because __munlock_folio() only clears the mlocked flag + * while the LRU lock is held. + * + * (That is not true of __page_cache_release(), and not necessarily + * true of folios_put(): but those only clear the mlocked flag after + * folio_put_testzero() has excluded any other users of the folio.) */ - unsigned long flags; - bool got = false; - struct page *page_head = compound_trans_head(page); - - if (likely(page != page_head && get_page_unless_zero(page_head))) { - - /* Ref to put_compound_page() comment. */ - if (PageSlab(page_head)) { - if (likely(PageTail(page))) { - __get_page_tail_foll(page, false); - return true; - } else { - put_page(page_head); - return false; - } - } - + if (folio_evictable(folio)) { + if (was_unevictable) + __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); + } else { + folio_clear_active(folio); + folio_set_unevictable(folio); /* - * page_head wasn't a dangling pointer but it - * may not be a head page anymore by the time - * we obtain the lock. That is ok as long as it - * can't be freed from under us. + * folio->mlock_count = !!folio_test_mlocked(folio)? + * But that leaves __mlock_folio() in doubt whether another + * actor has already counted the mlock or not. Err on the + * safe side, underestimate, let page reclaim fix it, rather + * than leaving a page on the unevictable LRU indefinitely. */ - flags = compound_lock_irqsave(page_head); - /* here __split_huge_page_refcount won't run anymore */ - if (likely(PageTail(page))) { - __get_page_tail_foll(page, false); - got = true; - } - compound_unlock_irqrestore(page_head, flags); - if (unlikely(!got)) - put_page(page_head); + folio->mlock_count = 0; + if (!was_unevictable) + __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); } - return got; + + lruvec_add_folio(lruvec, folio); + trace_mm_lru_insertion(folio); } -EXPORT_SYMBOL(__get_page_tail); -/** - * put_pages_list() - release a list of pages - * @pages: list of pages threaded on page->lru - * - * Release a list of pages which are strung together on page.lru. Currently - * used by read_cache_pages() and related error recovery code. - */ -void put_pages_list(struct list_head *pages) +static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) { - while (!list_empty(pages)) { - struct page *victim; + int i; + struct lruvec *lruvec = NULL; + unsigned long flags = 0; - victim = list_entry(pages->prev, struct page, lru); - list_del(&victim->lru); - page_cache_release(victim); - } -} -EXPORT_SYMBOL(put_pages_list); + for (i = 0; i < folio_batch_count(fbatch); i++) { + struct folio *folio = fbatch->folios[i]; -/* - * get_kernel_pages() - pin kernel pages in memory - * @kiov: An array of struct kvec structures - * @nr_segs: number of segments to pin - * @write: pinning for read/write, currently ignored - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_segs long. - * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. Each page returned must be released - * with a put_page() call when it is finished with. - */ -int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write, - struct page **pages) -{ - int seg; + /* block memcg migration while the folio moves between lru */ + if (move_fn != lru_add && !folio_test_clear_lru(folio)) + continue; - for (seg = 0; seg < nr_segs; seg++) { - if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE)) - return seg; + folio_lruvec_relock_irqsave(folio, &lruvec, &flags); + move_fn(lruvec, folio); - pages[seg] = kmap_to_page(kiov[seg].iov_base); - page_cache_get(pages[seg]); + folio_set_lru(folio); } - return seg; + if (lruvec) + unlock_page_lruvec_irqrestore(lruvec, flags); + folios_put(fbatch); } -EXPORT_SYMBOL_GPL(get_kernel_pages); -/* - * get_kernel_page() - pin a kernel page in memory - * @start: starting kernel address - * @write: pinning for read/write, currently ignored - * @pages: array that receives pointer to the page pinned. - * Must be at least nr_segs long. - * - * Returns 1 if page is pinned. If the page was not pinned, returns - * -errno. The page returned must be released with a put_page() call - * when it is finished with. - */ -int get_kernel_page(unsigned long start, int write, struct page **pages) +static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, + struct folio *folio, move_fn_t move_fn, bool disable_irq) { - const struct kvec kiov = { - .iov_base = (void *)start, - .iov_len = PAGE_SIZE - }; - - return get_kernel_pages(&kiov, 1, write, pages); -} -EXPORT_SYMBOL_GPL(get_kernel_page); + unsigned long flags; -static void pagevec_lru_move_fn(struct pagevec *pvec, - void (*move_fn)(struct page *page, struct lruvec *lruvec, void *arg), - void *arg) -{ - int i; - struct zone *zone = NULL; - struct lruvec *lruvec; - unsigned long flags = 0; + folio_get(folio); - for (i = 0; i < pagevec_count(pvec); i++) { - struct page *page = pvec->pages[i]; - struct zone *pagezone = page_zone(page); + if (disable_irq) + local_lock_irqsave(&cpu_fbatches.lock_irq, flags); + else + local_lock(&cpu_fbatches.lock); - if (pagezone != zone) { - if (zone) - spin_unlock_irqrestore(&zone->lru_lock, flags); - zone = pagezone; - spin_lock_irqsave(&zone->lru_lock, flags); - } + if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) + folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); - lruvec = mem_cgroup_page_lruvec(page, zone); - (*move_fn)(page, lruvec, arg); - } - if (zone) - spin_unlock_irqrestore(&zone->lru_lock, flags); - release_pages(pvec->pages, pvec->nr, pvec->cold); - pagevec_reinit(pvec); + if (disable_irq) + local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); + else + local_unlock(&cpu_fbatches.lock); } -static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec, - void *arg) +#define folio_batch_add_and_move(folio, op) \ + __folio_batch_add_and_move( \ + &cpu_fbatches.op, \ + folio, \ + op, \ + offsetof(struct cpu_fbatches, op) >= \ + offsetof(struct cpu_fbatches, lock_irq) \ + ) + +static void lru_move_tail(struct lruvec *lruvec, struct folio *folio) { - int *pgmoved = arg; + if (folio_test_unevictable(folio)) + return; - if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { - enum lru_list lru = page_lru_base_type(page); - list_move_tail(&page->lru, &lruvec->lists[lru]); - (*pgmoved)++; - } + lruvec_del_folio(lruvec, folio); + folio_clear_active(folio); + lruvec_add_folio_tail(lruvec, folio); + __count_vm_events(PGROTATED, folio_nr_pages(folio)); } /* - * pagevec_move_tail() must be called with IRQ disabled. - * Otherwise this may cause nasty races. + * Writeback is about to end against a folio which has been marked for + * immediate reclaim. If it still appears to be reclaimable, move it + * to the tail of the inactive list. + * + * folio_rotate_reclaimable() must disable IRQs, to prevent nasty races. */ -static void pagevec_move_tail(struct pagevec *pvec) +void folio_rotate_reclaimable(struct folio *folio) { - int pgmoved = 0; + if (folio_test_locked(folio) || folio_test_dirty(folio) || + folio_test_unevictable(folio) || !folio_test_lru(folio)) + return; - pagevec_lru_move_fn(pvec, pagevec_move_tail_fn, &pgmoved); - __count_vm_events(PGROTATED, pgmoved); + folio_batch_add_and_move(folio, lru_move_tail); } -/* - * Writeback is about to end against a page which has been marked for immediate - * reclaim. If it still appears to be reclaimable, move it to the tail of the - * inactive list. - */ -void rotate_reclaimable_page(struct page *page) +void lru_note_cost_unlock_irq(struct lruvec *lruvec, bool file, + unsigned int nr_io, unsigned int nr_rotated) + __releases(lruvec->lru_lock) { - if (!PageLocked(page) && !PageDirty(page) && !PageActive(page) && - !PageUnevictable(page) && PageLRU(page)) { - struct pagevec *pvec; - unsigned long flags; + unsigned long cost; - page_cache_get(page); - local_irq_save(flags); - pvec = &__get_cpu_var(lru_rotate_pvecs); - if (!pagevec_add(pvec, page)) - pagevec_move_tail(pvec); - local_irq_restore(flags); + /* + * Reflect the relative cost of incurring IO and spending CPU + * time on rotations. This doesn't attempt to make a precise + * comparison, it just says: if reloads are about comparable + * between the LRU lists, or rotations are overwhelmingly + * different between them, adjust scan balance for CPU work. + */ + cost = nr_io * SWAP_CLUSTER_MAX + nr_rotated; + if (!cost) { + spin_unlock_irq(&lruvec->lru_lock); + return; + } + + for (;;) { + unsigned long lrusize; + + /* Record cost event */ + if (file) + lruvec->file_cost += cost; + else + lruvec->anon_cost += cost; + + /* + * Decay previous events + * + * Because workloads change over time (and to avoid + * overflow) we keep these statistics as a floating + * average, which ends up weighing recent refaults + * more than old ones. + */ + lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) + + lruvec_page_state(lruvec, NR_ACTIVE_ANON) + + lruvec_page_state(lruvec, NR_INACTIVE_FILE) + + lruvec_page_state(lruvec, NR_ACTIVE_FILE); + + if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { + lruvec->file_cost /= 2; + lruvec->anon_cost /= 2; + } + + spin_unlock_irq(&lruvec->lru_lock); + lruvec = parent_lruvec(lruvec); + if (!lruvec) + break; + spin_lock_irq(&lruvec->lru_lock); } } -static void update_page_reclaim_stat(struct lruvec *lruvec, - int file, int rotated) +void lru_note_cost_refault(struct folio *folio) { - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; + struct lruvec *lruvec; - reclaim_stat->recent_scanned[file]++; - if (rotated) - reclaim_stat->recent_rotated[file]++; + lruvec = folio_lruvec_lock_irq(folio); + lru_note_cost_unlock_irq(lruvec, folio_is_file_lru(folio), + folio_nr_pages(folio), 0); } -static void __activate_page(struct page *page, struct lruvec *lruvec, - void *arg) +static void lru_activate(struct lruvec *lruvec, struct folio *folio) { - if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { - int file = page_is_file_cache(page); - int lru = page_lru_base_type(page); + long nr_pages = folio_nr_pages(folio); - del_page_from_lru_list(page, lruvec, lru); - SetPageActive(page); - lru += LRU_ACTIVE; - add_page_to_lru_list(page, lruvec, lru); - trace_mm_lru_activate(page, page_to_pfn(page)); + if (folio_test_active(folio) || folio_test_unevictable(folio)) + return; - __count_vm_event(PGACTIVATE); - update_page_reclaim_stat(lruvec, file, 1); - } + + lruvec_del_folio(lruvec, folio); + folio_set_active(folio); + lruvec_add_folio(lruvec, folio); + trace_mm_lru_activate(folio); + + __count_vm_events(PGACTIVATE, nr_pages); + count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages); } #ifdef CONFIG_SMP -static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs); - -static void activate_page_drain(int cpu) +static void folio_activate_drain(int cpu) { - struct pagevec *pvec = &per_cpu(activate_page_pvecs, cpu); + struct folio_batch *fbatch = &per_cpu(cpu_fbatches.lru_activate, cpu); - if (pagevec_count(pvec)) - pagevec_lru_move_fn(pvec, __activate_page, NULL); + if (folio_batch_count(fbatch)) + folio_batch_move_lru(fbatch, lru_activate); } -void activate_page(struct page *page) +void folio_activate(struct folio *folio) { - if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { - struct pagevec *pvec = &get_cpu_var(activate_page_pvecs); + if (folio_test_active(folio) || folio_test_unevictable(folio) || + !folio_test_lru(folio)) + return; - page_cache_get(page); - if (!pagevec_add(pvec, page)) - pagevec_lru_move_fn(pvec, __activate_page, NULL); - put_cpu_var(activate_page_pvecs); - } + folio_batch_add_and_move(folio, lru_activate); } #else -static inline void activate_page_drain(int cpu) +static inline void folio_activate_drain(int cpu) { } -void activate_page(struct page *page) +void folio_activate(struct folio *folio) { - struct zone *zone = page_zone(page); + struct lruvec *lruvec; - spin_lock_irq(&zone->lru_lock); - __activate_page(page, mem_cgroup_page_lruvec(page, zone), NULL); - spin_unlock_irq(&zone->lru_lock); + if (!folio_test_clear_lru(folio)) + return; + + lruvec = folio_lruvec_lock_irq(folio); + lru_activate(lruvec, folio); + unlock_page_lruvec_irq(lruvec); + folio_set_lru(folio); } #endif -static void __lru_cache_activate_page(struct page *page) +static void __lru_cache_activate_folio(struct folio *folio) { - struct pagevec *pvec = &get_cpu_var(lru_add_pvec); + struct folio_batch *fbatch; int i; + local_lock(&cpu_fbatches.lock); + fbatch = this_cpu_ptr(&cpu_fbatches.lru_add); + /* - * Search backwards on the optimistic assumption that the page being - * activated has just been added to this pagevec. Note that only - * the local pagevec is examined as a !PageLRU page could be in the + * Search backwards on the optimistic assumption that the folio being + * activated has just been added to this batch. Note that only + * the local batch is examined as a !LRU folio could be in the * process of being released, reclaimed, migrated or on a remote - * pagevec that is currently being drained. Furthermore, marking - * a remote pagevec's page PageActive potentially hits a race where - * a page is marked PageActive just after it is added to the inactive + * batch that is currently being drained. Furthermore, marking + * a remote batch's folio active potentially hits a race where + * a folio is marked active just after it is added to the inactive * list causing accounting errors and BUG_ON checks to trigger. */ - for (i = pagevec_count(pvec) - 1; i >= 0; i--) { - struct page *pagevec_page = pvec->pages[i]; + for (i = folio_batch_count(fbatch) - 1; i >= 0; i--) { + struct folio *batch_folio = fbatch->folios[i]; - if (pagevec_page == page) { - SetPageActive(page); + if (batch_folio == folio) { + folio_set_active(folio); break; } } - put_cpu_var(lru_add_pvec); + local_unlock(&cpu_fbatches.lock); } -/* - * Mark a page as having seen activity. +#ifdef CONFIG_LRU_GEN + +static void lru_gen_inc_refs(struct folio *folio) +{ + unsigned long new_flags, old_flags = READ_ONCE(folio->flags.f); + + if (folio_test_unevictable(folio)) + return; + + /* see the comment on LRU_REFS_FLAGS */ + if (!folio_test_referenced(folio)) { + set_mask_bits(&folio->flags.f, LRU_REFS_MASK, BIT(PG_referenced)); + return; + } + + do { + if ((old_flags & LRU_REFS_MASK) == LRU_REFS_MASK) { + if (!folio_test_workingset(folio)) + folio_set_workingset(folio); + return; + } + + new_flags = old_flags + BIT(LRU_REFS_PGOFF); + } while (!try_cmpxchg(&folio->flags.f, &old_flags, new_flags)); +} + +static bool lru_gen_clear_refs(struct folio *folio) +{ + struct lru_gen_folio *lrugen; + int gen = folio_lru_gen(folio); + int type = folio_is_file_lru(folio); + + if (gen < 0) + return true; + + set_mask_bits(&folio->flags.f, LRU_REFS_FLAGS | BIT(PG_workingset), 0); + + lrugen = &folio_lruvec(folio)->lrugen; + /* whether can do without shuffling under the LRU lock */ + return gen == lru_gen_from_seq(READ_ONCE(lrugen->min_seq[type])); +} + +#else /* !CONFIG_LRU_GEN */ + +static void lru_gen_inc_refs(struct folio *folio) +{ +} + +static bool lru_gen_clear_refs(struct folio *folio) +{ + return false; +} + +#endif /* CONFIG_LRU_GEN */ + +/** + * folio_mark_accessed - Mark a folio as having seen activity. + * @folio: The folio to mark. + * + * This function will perform one of the following transitions: * - * inactive,unreferenced -> inactive,referenced - * inactive,referenced -> active,unreferenced - * active,unreferenced -> active,referenced + * * inactive,unreferenced -> inactive,referenced + * * inactive,referenced -> active,unreferenced + * * active,unreferenced -> active,referenced + * + * When a newly allocated folio is not yet visible, so safe for non-atomic ops, + * __folio_set_referenced() may be substituted for folio_mark_accessed(). */ -void mark_page_accessed(struct page *page) +void folio_mark_accessed(struct folio *folio) { - if (!PageActive(page) && !PageUnevictable(page) && - PageReferenced(page)) { + if (folio_test_dropbehind(folio)) + return; + if (lru_gen_enabled()) { + lru_gen_inc_refs(folio); + return; + } + if (!folio_test_referenced(folio)) { + folio_set_referenced(folio); + } else if (folio_test_unevictable(folio)) { + /* + * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, + * this list is never rotated or maintained, so marking an + * unevictable page accessed has no effect. + */ + } else if (!folio_test_active(folio)) { /* - * If the page is on the LRU, queue it for activation via - * activate_page_pvecs. Otherwise, assume the page is on a - * pagevec, mark it active and it'll be moved to the active + * If the folio is on the LRU, queue it for activation via + * cpu_fbatches.lru_activate. Otherwise, assume the folio is in a + * folio_batch, mark it active and it'll be moved to the active * LRU on the next drain. */ - if (PageLRU(page)) - activate_page(page); + if (folio_test_lru(folio)) + folio_activate(folio); else - __lru_cache_activate_page(page); - ClearPageReferenced(page); - } else if (!PageReferenced(page)) { - SetPageReferenced(page); + __lru_cache_activate_folio(folio); + folio_clear_referenced(folio); + workingset_activation(folio); } + if (folio_test_idle(folio)) + folio_clear_idle(folio); } -EXPORT_SYMBOL(mark_page_accessed); +EXPORT_SYMBOL(folio_mark_accessed); -/* - * Queue the page for addition to the LRU via pagevec. The decision on whether +/** + * folio_add_lru - Add a folio to an LRU list. + * @folio: The folio to be added to the LRU. + * + * Queue the folio for addition to the LRU. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the - * pagevec is drained. This gives a chance for the caller of __lru_cache_add() - * have the page added to the active list using mark_page_accessed(). + * folio_batch is drained. This gives a chance for the caller of folio_add_lru() + * have the folio added to the active list using folio_mark_accessed(). */ -void __lru_cache_add(struct page *page) +void folio_add_lru(struct folio *folio) { - struct pagevec *pvec = &get_cpu_var(lru_add_pvec); - - page_cache_get(page); - if (!pagevec_space(pvec)) - __pagevec_lru_add(pvec); - pagevec_add(pvec, page); - put_cpu_var(lru_add_pvec); -} -EXPORT_SYMBOL(__lru_cache_add); + VM_BUG_ON_FOLIO(folio_test_active(folio) && + folio_test_unevictable(folio), folio); + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); -/** - * lru_cache_add - add a page to a page list - * @page: the page to be added to the LRU. - */ -void lru_cache_add(struct page *page) -{ - if (PageActive(page)) { - VM_BUG_ON(PageUnevictable(page)); - } else if (PageUnevictable(page)) { - VM_BUG_ON(PageActive(page)); - } + /* see the comment in lru_gen_folio_seq() */ + if (lru_gen_enabled() && !folio_test_unevictable(folio) && + lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) + folio_set_active(folio); - VM_BUG_ON(PageLRU(page)); - __lru_cache_add(page); + folio_batch_add_and_move(folio, lru_add); } +EXPORT_SYMBOL(folio_add_lru); /** - * add_page_to_unevictable_list - add a page to the unevictable list - * @page: the page to be added to the unevictable list + * folio_add_lru_vma() - Add a folio to the appropate LRU list for this VMA. + * @folio: The folio to be added to the LRU. + * @vma: VMA in which the folio is mapped. * - * Add page directly to its zone's unevictable list. To avoid races with - * tasks that might be making the page evictable, through eg. munlock, - * munmap or exit, while it's not on the lru, we want to add the page - * while it's locked or otherwise "invisible" to other tasks. This is - * difficult to do when using the pagevec cache, so bypass that. + * If the VMA is mlocked, @folio is added to the unevictable list. + * Otherwise, it is treated the same way as folio_add_lru(). */ -void add_page_to_unevictable_list(struct page *page) +void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma) { - struct zone *zone = page_zone(page); - struct lruvec *lruvec; + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); - spin_lock_irq(&zone->lru_lock); - lruvec = mem_cgroup_page_lruvec(page, zone); - SetPageUnevictable(page); - SetPageLRU(page); - add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE); - spin_unlock_irq(&zone->lru_lock); + if (unlikely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED)) + mlock_new_folio(folio); + else + folio_add_lru(folio); } /* - * If the page can not be invalidated, it is moved to the + * If the folio cannot be invalidated, it is moved to the * inactive list to speed up its reclaim. It is moved to the * head of the list, rather than the tail, to give the flusher * threads some time to write it out, as this is much more * effective than the single-page writeout from reclaim. * - * If the page isn't page_mapped and dirty/writeback, the page - * could reclaim asap using PG_reclaim. + * If the folio isn't mapped and dirty/writeback, the folio + * could be reclaimed asap using the reclaim flag. * - * 1. active, mapped page -> none - * 2. active, dirty/writeback page -> inactive, head, PG_reclaim - * 3. inactive, mapped page -> none - * 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim + * 1. active, mapped folio -> none + * 2. active, dirty/writeback folio -> inactive, head, reclaim + * 3. inactive, mapped folio -> none + * 4. inactive, dirty/writeback folio -> inactive, head, reclaim * 5. inactive, clean -> inactive, tail * 6. Others -> none * - * In 4, why it moves inactive's head, the VM expects the page would - * be write it out by flusher threads as this is much more effective + * In 4, it moves to the head of the inactive list so the folio is + * written out by flusher threads as this is much more efficient * than the single-page writeout from reclaim. */ -static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, - void *arg) +static void lru_deactivate_file(struct lruvec *lruvec, struct folio *folio) { - int lru, file; - bool active; - - if (!PageLRU(page)) - return; + bool active = folio_test_active(folio) || lru_gen_enabled(); + long nr_pages = folio_nr_pages(folio); - if (PageUnevictable(page)) + if (folio_test_unevictable(folio)) return; - /* Some processes are using the page */ - if (page_mapped(page)) + /* Some processes are using the folio */ + if (folio_mapped(folio)) return; - active = PageActive(page); - file = page_is_file_cache(page); - lru = page_lru_base_type(page); + lruvec_del_folio(lruvec, folio); + folio_clear_active(folio); + folio_clear_referenced(folio); - del_page_from_lru_list(page, lruvec, lru + active); - ClearPageActive(page); - ClearPageReferenced(page); - add_page_to_lru_list(page, lruvec, lru); - - if (PageWriteback(page) || PageDirty(page)) { + if (folio_test_writeback(folio) || folio_test_dirty(folio)) { /* - * PG_reclaim could be raced with end_page_writeback - * It can make readahead confusing. But race window - * is _really_ small and it's non-critical problem. + * Setting the reclaim flag could race with + * folio_end_writeback() and confuse readahead. But the + * race window is _really_ small and it's not a critical + * problem. */ - SetPageReclaim(page); + lruvec_add_folio(lruvec, folio); + folio_set_reclaim(folio); } else { /* - * The page's writeback ends up during pagevec - * We moves tha page into tail of inactive. + * The folio's writeback ended while it was in the batch. + * We move that folio to the tail of the inactive list. */ - list_move_tail(&page->lru, &lruvec->lists[lru]); - __count_vm_event(PGROTATED); + lruvec_add_folio_tail(lruvec, folio); + __count_vm_events(PGROTATED, nr_pages); } - if (active) - __count_vm_event(PGDEACTIVATE); - update_page_reclaim_stat(lruvec, file, 0); + if (active) { + __count_vm_events(PGDEACTIVATE, nr_pages); + count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, + nr_pages); + } +} + +static void lru_deactivate(struct lruvec *lruvec, struct folio *folio) +{ + long nr_pages = folio_nr_pages(folio); + + if (folio_test_unevictable(folio) || !(folio_test_active(folio) || lru_gen_enabled())) + return; + + lruvec_del_folio(lruvec, folio); + folio_clear_active(folio); + folio_clear_referenced(folio); + lruvec_add_folio(lruvec, folio); + + __count_vm_events(PGDEACTIVATE, nr_pages); + count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); +} + +static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio) +{ + long nr_pages = folio_nr_pages(folio); + + if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || + folio_test_swapcache(folio) || folio_test_unevictable(folio)) + return; + + lruvec_del_folio(lruvec, folio); + folio_clear_active(folio); + if (lru_gen_enabled()) + lru_gen_clear_refs(folio); + else + folio_clear_referenced(folio); + /* + * Lazyfree folios are clean anonymous folios. They have + * the swapbacked flag cleared, to distinguish them from normal + * anonymous folios + */ + folio_clear_swapbacked(folio); + lruvec_add_folio(lruvec, folio); + + __count_vm_events(PGLAZYFREE, nr_pages); + count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages); } /* - * Drain pages out of the cpu's pagevecs. + * Drain pages out of the cpu's folio_batch. * Either "cpu" is the current CPU, and preemption has already been * disabled; or "cpu" is being hot-unplugged, and is already dead. */ void lru_add_drain_cpu(int cpu) { - struct pagevec *pvec = &per_cpu(lru_add_pvec, cpu); + struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); + struct folio_batch *fbatch = &fbatches->lru_add; - if (pagevec_count(pvec)) - __pagevec_lru_add(pvec); + if (folio_batch_count(fbatch)) + folio_batch_move_lru(fbatch, lru_add); - pvec = &per_cpu(lru_rotate_pvecs, cpu); - if (pagevec_count(pvec)) { + fbatch = &fbatches->lru_move_tail; + /* Disabling interrupts below acts as a compiler barrier. */ + if (data_race(folio_batch_count(fbatch))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ - local_irq_save(flags); - pagevec_move_tail(pvec); - local_irq_restore(flags); + local_lock_irqsave(&cpu_fbatches.lock_irq, flags); + folio_batch_move_lru(fbatch, lru_move_tail); + local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); } - pvec = &per_cpu(lru_deactivate_pvecs, cpu); - if (pagevec_count(pvec)) - pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); + fbatch = &fbatches->lru_deactivate_file; + if (folio_batch_count(fbatch)) + folio_batch_move_lru(fbatch, lru_deactivate_file); + + fbatch = &fbatches->lru_deactivate; + if (folio_batch_count(fbatch)) + folio_batch_move_lru(fbatch, lru_deactivate); + + fbatch = &fbatches->lru_lazyfree; + if (folio_batch_count(fbatch)) + folio_batch_move_lru(fbatch, lru_lazyfree); - activate_page_drain(cpu); + folio_activate_drain(cpu); } /** - * deactivate_page - forcefully deactivate a page - * @page: page to deactivate + * deactivate_file_folio() - Deactivate a file folio. + * @folio: Folio to deactivate. * - * This function hints the VM that @page is a good reclaim candidate, - * for example if its invalidation fails due to the page being dirty + * This function hints to the VM that @folio is a good reclaim candidate, + * for example if its invalidation fails due to the folio being dirty * or under writeback. + * + * Context: Caller holds a reference on the folio. */ -void deactivate_page(struct page *page) +void deactivate_file_folio(struct folio *folio) { - /* - * In a workload with many unevictable page such as mprotect, unevictable - * page deactivation for accelerating reclaim is pointless. - */ - if (PageUnevictable(page)) + /* Deactivating an unevictable folio will not accelerate reclaim */ + if (folio_test_unevictable(folio) || !folio_test_lru(folio)) + return; + + if (lru_gen_enabled() && lru_gen_clear_refs(folio)) return; - if (likely(get_page_unless_zero(page))) { - struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs); + folio_batch_add_and_move(folio, lru_deactivate_file); +} - if (!pagevec_add(pvec, page)) - pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); - put_cpu_var(lru_deactivate_pvecs); - } +/* + * folio_deactivate - deactivate a folio + * @folio: folio to deactivate + * + * folio_deactivate() moves @folio to the inactive list if @folio was on the + * active list and was not unevictable. This is done to accelerate the + * reclaim of @folio. + */ +void folio_deactivate(struct folio *folio) +{ + if (folio_test_unevictable(folio) || !folio_test_lru(folio)) + return; + + if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio)) + return; + + folio_batch_add_and_move(folio, lru_deactivate); +} + +/** + * folio_mark_lazyfree - make an anon folio lazyfree + * @folio: folio to deactivate + * + * folio_mark_lazyfree() moves @folio to the inactive file list. + * This is done to accelerate the reclaim of @folio. + */ +void folio_mark_lazyfree(struct folio *folio) +{ + if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || + !folio_test_lru(folio) || + folio_test_swapcache(folio) || folio_test_unevictable(folio)) + return; + + folio_batch_add_and_move(folio, lru_lazyfree); } void lru_add_drain(void) { - lru_add_drain_cpu(get_cpu()); - put_cpu(); + local_lock(&cpu_fbatches.lock); + lru_add_drain_cpu(smp_processor_id()); + local_unlock(&cpu_fbatches.lock); + mlock_drain_local(); } +/* + * It's called from per-cpu workqueue context in SMP case so + * lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on + * the same cpu. It shouldn't be a problem in !SMP case since + * the core is only one and the locks will disable preemption. + */ +static void lru_add_and_bh_lrus_drain(void) +{ + local_lock(&cpu_fbatches.lock); + lru_add_drain_cpu(smp_processor_id()); + local_unlock(&cpu_fbatches.lock); + invalidate_bh_lrus_cpu(); + mlock_drain_local(); +} + +void lru_add_drain_cpu_zone(struct zone *zone) +{ + local_lock(&cpu_fbatches.lock); + lru_add_drain_cpu(smp_processor_id()); + drain_local_pages(zone); + local_unlock(&cpu_fbatches.lock); + mlock_drain_local(); +} + +#ifdef CONFIG_SMP + +static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); + static void lru_add_drain_per_cpu(struct work_struct *dummy) { - lru_add_drain(); + lru_add_and_bh_lrus_drain(); +} + +static bool cpu_needs_drain(unsigned int cpu) +{ + struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); + + /* Check these in order of likelihood that they're not zero */ + return folio_batch_count(&fbatches->lru_add) || + folio_batch_count(&fbatches->lru_move_tail) || + folio_batch_count(&fbatches->lru_deactivate_file) || + folio_batch_count(&fbatches->lru_deactivate) || + folio_batch_count(&fbatches->lru_lazyfree) || + folio_batch_count(&fbatches->lru_activate) || + need_mlock_drain(cpu) || + has_bh_in_lru(cpu, NULL); } /* - * Returns 0 for success + * Doesn't need any cpu hotplug locking because we do rely on per-cpu + * kworkers being shut down before our page_alloc_cpu_dead callback is + * executed on the offlined cpu. + * Calling this function with cpu hotplug locks held can actually lead + * to obscure indirect dependencies via WQ context. */ -int lru_add_drain_all(void) +static inline void __lru_add_drain_all(bool force_all_cpus) +{ + /* + * lru_drain_gen - Global pages generation number + * + * (A) Definition: global lru_drain_gen = x implies that all generations + * 0 < n <= x are already *scheduled* for draining. + * + * This is an optimization for the highly-contended use case where a + * user space workload keeps constantly generating a flow of pages for + * each CPU. + */ + static unsigned int lru_drain_gen; + static struct cpumask has_work; + static DEFINE_MUTEX(lock); + unsigned cpu, this_gen; + + /* + * Make sure nobody triggers this path before mm_percpu_wq is fully + * initialized. + */ + if (WARN_ON(!mm_percpu_wq)) + return; + + /* + * Guarantee folio_batch counter stores visible by this CPU + * are visible to other CPUs before loading the current drain + * generation. + */ + smp_mb(); + + /* + * (B) Locally cache global LRU draining generation number + * + * The read barrier ensures that the counter is loaded before the mutex + * is taken. It pairs with smp_mb() inside the mutex critical section + * at (D). + */ + this_gen = smp_load_acquire(&lru_drain_gen); + + /* It helps everyone if we do our own local drain immediately. */ + lru_add_drain(); + + mutex_lock(&lock); + + /* + * (C) Exit the draining operation if a newer generation, from another + * lru_add_drain_all(), was already scheduled for draining. Check (A). + */ + if (unlikely(this_gen != lru_drain_gen && !force_all_cpus)) + goto done; + + /* + * (D) Increment global generation number + * + * Pairs with smp_load_acquire() at (B), outside of the critical + * section. Use a full memory barrier to guarantee that the + * new global drain generation number is stored before loading + * folio_batch counters. + * + * This pairing must be done here, before the for_each_online_cpu loop + * below which drains the page vectors. + * + * Let x, y, and z represent some system CPU numbers, where x < y < z. + * Assume CPU #z is in the middle of the for_each_online_cpu loop + * below and has already reached CPU #y's per-cpu data. CPU #x comes + * along, adds some pages to its per-cpu vectors, then calls + * lru_add_drain_all(). + * + * If the paired barrier is done at any later step, e.g. after the + * loop, CPU #x will just exit at (C) and miss flushing out all of its + * added pages. + */ + WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1); + smp_mb(); + + cpumask_clear(&has_work); + for_each_online_cpu(cpu) { + struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); + + if (cpu_needs_drain(cpu)) { + INIT_WORK(work, lru_add_drain_per_cpu); + queue_work_on(cpu, mm_percpu_wq, work); + __cpumask_set_cpu(cpu, &has_work); + } + } + + for_each_cpu(cpu, &has_work) + flush_work(&per_cpu(lru_add_drain_work, cpu)); + +done: + mutex_unlock(&lock); +} + +void lru_add_drain_all(void) { - return schedule_on_each_cpu(lru_add_drain_per_cpu); + __lru_add_drain_all(false); } +#else +void lru_add_drain_all(void) +{ + lru_add_drain(); +} +#endif /* CONFIG_SMP */ + +atomic_t lru_disable_count = ATOMIC_INIT(0); /* - * Batched page_cache_release(). Decrement the reference count on all the - * passed pages. If it fell to zero then remove the page from the LRU and - * free it. + * lru_cache_disable() needs to be called before we start compiling + * a list of folios to be migrated using folio_isolate_lru(). + * It drains folios on LRU cache and then disable on all cpus until + * lru_cache_enable is called. + * + * Must be paired with a call to lru_cache_enable(). + */ +void lru_cache_disable(void) +{ + atomic_inc(&lru_disable_count); + /* + * Readers of lru_disable_count are protected by either disabling + * preemption or rcu_read_lock: + * + * preempt_disable, local_irq_disable [bh_lru_lock()] + * rcu_read_lock [rt_spin_lock CONFIG_PREEMPT_RT] + * preempt_disable [local_lock !CONFIG_PREEMPT_RT] + * + * Since v5.1 kernel, synchronize_rcu() is guaranteed to wait on + * preempt_disable() regions of code. So any CPU which sees + * lru_disable_count = 0 will have exited the critical + * section when synchronize_rcu() returns. + */ + synchronize_rcu_expedited(); +#ifdef CONFIG_SMP + __lru_add_drain_all(true); +#else + lru_add_and_bh_lrus_drain(); +#endif +} + +/** + * folios_put_refs - Reduce the reference count on a batch of folios. + * @folios: The folios. + * @refs: The number of refs to subtract from each folio. * - * Avoid taking zone->lru_lock if possible, but if it is taken, retain it - * for the remainder of the operation. + * Like folio_put(), but for a batch of folios. This is more efficient + * than writing the loop yourself as it will optimise the locks which need + * to be taken if the folios are freed. The folios batch is returned + * empty and ready to be reused for another batch; there is no need + * to reinitialise it. If @refs is NULL, we subtract one from each + * folio refcount. * - * The locking in this function is against shrink_inactive_list(): we recheck - * the page count inside the lock to see whether shrink_inactive_list() - * grabbed the page via the LRU. If it did, give up: shrink_inactive_list() - * will free it. + * Context: May be called in process or interrupt context, but not in NMI + * context. May be called while holding a spinlock. */ -void release_pages(struct page **pages, int nr, int cold) +void folios_put_refs(struct folio_batch *folios, unsigned int *refs) { - int i; - LIST_HEAD(pages_to_free); - struct zone *zone = NULL; - struct lruvec *lruvec; - unsigned long uninitialized_var(flags); + int i, j; + struct lruvec *lruvec = NULL; + unsigned long flags = 0; - for (i = 0; i < nr; i++) { - struct page *page = pages[i]; + for (i = 0, j = 0; i < folios->nr; i++) { + struct folio *folio = folios->folios[i]; + unsigned int nr_refs = refs ? refs[i] : 1; + + if (is_huge_zero_folio(folio)) + continue; - if (unlikely(PageCompound(page))) { - if (zone) { - spin_unlock_irqrestore(&zone->lru_lock, flags); - zone = NULL; + if (folio_is_zone_device(folio)) { + if (lruvec) { + unlock_page_lruvec_irqrestore(lruvec, flags); + lruvec = NULL; } - put_compound_page(page); + if (folio_ref_sub_and_test(folio, nr_refs)) + free_zone_device_folio(folio); continue; } - if (!put_page_testzero(page)) + if (!folio_ref_sub_and_test(folio, nr_refs)) continue; - if (PageLRU(page)) { - struct zone *pagezone = page_zone(page); - - if (pagezone != zone) { - if (zone) - spin_unlock_irqrestore(&zone->lru_lock, - flags); - zone = pagezone; - spin_lock_irqsave(&zone->lru_lock, flags); + /* hugetlb has its own memcg */ + if (folio_test_hugetlb(folio)) { + if (lruvec) { + unlock_page_lruvec_irqrestore(lruvec, flags); + lruvec = NULL; } - - lruvec = mem_cgroup_page_lruvec(page, zone); - VM_BUG_ON(!PageLRU(page)); - __ClearPageLRU(page); - del_page_from_lru_list(page, lruvec, page_off_lru(page)); + free_huge_folio(folio); + continue; } + folio_unqueue_deferred_split(folio); + __page_cache_release(folio, &lruvec, &flags); - /* Clear Active bit in case of parallel mark_page_accessed */ - ClearPageActive(page); - - list_add(&page->lru, &pages_to_free); + if (j != i) + folios->folios[j] = folio; + j++; + } + if (lruvec) + unlock_page_lruvec_irqrestore(lruvec, flags); + if (!j) { + folio_batch_reinit(folios); + return; } - if (zone) - spin_unlock_irqrestore(&zone->lru_lock, flags); - free_hot_cold_page_list(&pages_to_free, cold); + folios->nr = j; + mem_cgroup_uncharge_folios(folios); + free_unref_folios(folios); } -EXPORT_SYMBOL(release_pages); +EXPORT_SYMBOL(folios_put_refs); -/* - * The pages which we're about to release may be in the deferred lru-addition - * queues. That would prevent them from really being freed right now. That's - * OK from a correctness point of view but is inefficient - those pages may be - * cache-warm and we want to give them back to the page allocator ASAP. +/** + * release_pages - batched put_page() + * @arg: array of pages to release + * @nr: number of pages * - * So __pagevec_release() will drain those queues here. __pagevec_lru_add() - * and __pagevec_lru_add_active() call release_pages() directly to avoid - * mutual recursion. + * Decrement the reference count on all the pages in @arg. If it + * fell to zero, remove the page from the LRU and free it. + * + * Note that the argument can be an array of pages, encoded pages, + * or folio pointers. We ignore any encoded bits, and turn any of + * them into just a folio that gets free'd. */ -void __pagevec_release(struct pagevec *pvec) +void release_pages(release_pages_arg arg, int nr) { - lru_add_drain(); - release_pages(pvec->pages, pagevec_count(pvec), pvec->cold); - pagevec_reinit(pvec); -} -EXPORT_SYMBOL(__pagevec_release); - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -/* used by __split_huge_page_refcount() */ -void lru_add_page_tail(struct page *page, struct page *page_tail, - struct lruvec *lruvec, struct list_head *list) -{ - int uninitialized_var(active); - enum lru_list lru; - const int file = 0; - - VM_BUG_ON(!PageHead(page)); - VM_BUG_ON(PageCompound(page_tail)); - VM_BUG_ON(PageLRU(page_tail)); - VM_BUG_ON(NR_CPUS != 1 && - !spin_is_locked(&lruvec_zone(lruvec)->lru_lock)); - - if (!list) - SetPageLRU(page_tail); - - if (page_evictable(page_tail)) { - if (PageActive(page)) { - SetPageActive(page_tail); - active = 1; - lru = LRU_ACTIVE_ANON; - } else { - active = 0; - lru = LRU_INACTIVE_ANON; - } - } else { - SetPageUnevictable(page_tail); - lru = LRU_UNEVICTABLE; - } - - if (likely(PageLRU(page))) - list_add_tail(&page_tail->lru, &page->lru); - else if (list) { - /* page reclaim is reclaiming a huge page */ - get_page(page_tail); - list_add_tail(&page_tail->lru, list); - } else { - struct list_head *list_head; - /* - * Head page has not yet been counted, as an hpage, - * so we must account for each subpage individually. - * - * Use the standard add function to put page_tail on the list, - * but then correct its position so they all end up in order. - */ - add_page_to_lru_list(page_tail, lruvec, lru); - list_head = page_tail->lru.prev; - list_move_tail(&page_tail->lru, list_head); - } + struct folio_batch fbatch; + int refs[PAGEVEC_SIZE]; + struct encoded_page **encoded = arg.encoded_pages; + int i; - if (!PageUnevictable(page)) - update_page_reclaim_stat(lruvec, file, active); -} -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + folio_batch_init(&fbatch); + for (i = 0; i < nr; i++) { + /* Turn any of the argument types into a folio */ + struct folio *folio = page_folio(encoded_page_ptr(encoded[i])); -static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec, - void *arg) -{ - int file = page_is_file_cache(page); - int active = PageActive(page); - enum lru_list lru = page_lru(page); + /* Is our next entry actually "nr_pages" -> "nr_refs" ? */ + refs[fbatch.nr] = 1; + if (unlikely(encoded_page_flags(encoded[i]) & + ENCODED_PAGE_BIT_NR_PAGES_NEXT)) + refs[fbatch.nr] = encoded_nr_pages(encoded[++i]); - VM_BUG_ON(PageUnevictable(page)); - VM_BUG_ON(PageLRU(page)); + if (folio_batch_add(&fbatch, folio) > 0) + continue; + folios_put_refs(&fbatch, refs); + } - SetPageLRU(page); - add_page_to_lru_list(page, lruvec, lru); - update_page_reclaim_stat(lruvec, file, active); - trace_mm_lru_insertion(page, page_to_pfn(page), lru, trace_pagemap_flags(page)); + if (fbatch.nr) + folios_put_refs(&fbatch, refs); } +EXPORT_SYMBOL(release_pages); /* - * Add the passed pages to the LRU, then drop the caller's refcount - * on them. Reinitialises the caller's pagevec. + * The folios which we're about to release may be in the deferred lru-addition + * queues. That would prevent them from really being freed right now. That's + * OK from a correctness point of view but is inefficient - those folios may be + * cache-warm and we want to give them back to the page allocator ASAP. + * + * So __folio_batch_release() will drain those queues here. + * folio_batch_move_lru() calls folios_put() directly to avoid + * mutual recursion. */ -void __pagevec_lru_add(struct pagevec *pvec) +void __folio_batch_release(struct folio_batch *fbatch) { - pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, NULL); + if (!fbatch->percpu_pvec_drained) { + lru_add_drain(); + fbatch->percpu_pvec_drained = true; + } + folios_put(fbatch); } -EXPORT_SYMBOL(__pagevec_lru_add); +EXPORT_SYMBOL(__folio_batch_release); /** - * pagevec_lookup - gang pagecache lookup - * @pvec: Where the resulting pages are placed - * @mapping: The address_space to search - * @start: The starting page index - * @nr_pages: The maximum number of pages - * - * pagevec_lookup() will search for and return a group of up to @nr_pages pages - * in the mapping. The pages are placed in @pvec. pagevec_lookup() takes a - * reference against the pages in @pvec. + * folio_batch_remove_exceptionals() - Prune non-folios from a batch. + * @fbatch: The batch to prune * - * The search returns a group of mapping-contiguous pages with ascending - * indexes. There may be holes in the indices due to not-present pages. - * - * pagevec_lookup() returns the number of pages which were found. + * find_get_entries() fills a batch with both folios and shadow/swap/DAX + * entries. This function prunes all the non-folio entries from @fbatch + * without leaving holes, so that it can be passed on to folio-only batch + * operations. */ -unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, - pgoff_t start, unsigned nr_pages) +void folio_batch_remove_exceptionals(struct folio_batch *fbatch) { - pvec->nr = find_get_pages(mapping, start, nr_pages, pvec->pages); - return pagevec_count(pvec); -} -EXPORT_SYMBOL(pagevec_lookup); + unsigned int i, j; -unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping, - pgoff_t *index, int tag, unsigned nr_pages) -{ - pvec->nr = find_get_pages_tag(mapping, index, tag, - nr_pages, pvec->pages); - return pagevec_count(pvec); + for (i = 0, j = 0; i < folio_batch_count(fbatch); i++) { + struct folio *folio = fbatch->folios[i]; + if (!xa_is_value(folio)) + fbatch->folios[j++] = folio; + } + fbatch->nr = j; } -EXPORT_SYMBOL(pagevec_lookup_tag); + +static const struct ctl_table swap_sysctl_table[] = { + { + .procname = "page-cluster", + .data = &page_cluster, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = (void *)&page_cluster_max, + } +}; /* * Perform any setup for the swap system */ void __init swap_setup(void) { - unsigned long megs = totalram_pages >> (20 - PAGE_SHIFT); -#ifdef CONFIG_SWAP - int i; - - bdi_init(swapper_spaces[0].backing_dev_info); - for (i = 0; i < MAX_SWAPFILES; i++) { - spin_lock_init(&swapper_spaces[i].tree_lock); - INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear); - } -#endif + unsigned long megs = PAGES_TO_MB(totalram_pages()); /* Use a smaller cluster for small-memory machines */ if (megs < 16) @@ -910,4 +1112,6 @@ void __init swap_setup(void) * Right now other parts of the system means that we * _really_ don't want to cluster much more */ + + register_sysctl_init("vm", swap_sysctl_table); } |