// SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swap.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * This file contains the default values for the operation of the * Linux VM subsystem. Fine-tuning documentation can be found in * 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. */ #include <linux/mm.h> #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/init.h> #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> #include <linux/backing-dev.h> #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? As a power of 2 */ int page_cluster; const int page_cluster_max = …; /* Protecting only lru_rotate.fbatch which requires disabling interrupts */ struct lru_rotate { … }; static DEFINE_PER_CPU(struct lru_rotate, lru_rotate) = …; /* * The following folio batches are grouped together because they are protected * by disabling preemption (and interrupts remain enabled). */ struct cpu_fbatches { … }; static DEFINE_PER_CPU(struct cpu_fbatches, cpu_fbatches) = …; static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp, unsigned long *flagsp) { … } /* * 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) { … } void __folio_put(struct folio *folio) { … } EXPORT_SYMBOL(…); /** * 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. */ void put_pages_list(struct list_head *pages) { … } EXPORT_SYMBOL(…); move_fn_t; static void lru_add_fn(struct lruvec *lruvec, struct folio *folio) { … } static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) { … } static void folio_batch_add_and_move(struct folio_batch *fbatch, struct folio *folio, move_fn_t move_fn) { … } static void lru_move_tail_fn(struct lruvec *lruvec, struct folio *folio) { … } /* * 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. */ void folio_rotate_reclaimable(struct folio *folio) { … } void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_io, unsigned int nr_rotated) { … } void lru_note_cost_refault(struct folio *folio) { … } static void folio_activate_fn(struct lruvec *lruvec, struct folio *folio) { … } #ifdef CONFIG_SMP static void folio_activate_drain(int cpu) { … } void folio_activate(struct folio *folio) { … } #else static inline void folio_activate_drain(int cpu) { } void folio_activate(struct folio *folio) { struct lruvec *lruvec; if (folio_test_clear_lru(folio)) { lruvec = folio_lruvec_lock_irq(folio); folio_activate_fn(lruvec, folio); unlock_page_lruvec_irq(lruvec); folio_set_lru(folio); } } #endif static void __lru_cache_activate_folio(struct folio *folio) { … } #ifdef CONFIG_LRU_GEN static void folio_inc_refs(struct folio *folio) { … } #else static void folio_inc_refs(struct folio *folio) { } #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 * * 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 folio_mark_accessed(struct folio *folio) { … } EXPORT_SYMBOL(…); /** * 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 * 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 folio_add_lru(struct folio *folio) { … } EXPORT_SYMBOL(…); /** * 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. * * If the VMA is mlocked, @folio is added to the unevictable list. * Otherwise, it is treated the same way as folio_add_lru(). */ void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma) { … } /* * 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 folio isn't mapped and dirty/writeback, the folio * could be reclaimed asap using the reclaim flag. * * 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, 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_file_fn(struct lruvec *lruvec, struct folio *folio) { … } static void lru_deactivate_fn(struct lruvec *lruvec, struct folio *folio) { … } static void lru_lazyfree_fn(struct lruvec *lruvec, struct folio *folio) { … } /* * 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) { … } /** * deactivate_file_folio() - Deactivate a file folio. * @folio: Folio to deactivate. * * 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_file_folio(struct folio *folio) { … } /* * 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) { … } /** * 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) { … } void lru_add_drain(void) { … } /* * 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) { … } void lru_add_drain_cpu_zone(struct zone *zone) { … } #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) { … } static bool cpu_needs_drain(unsigned int cpu) { … } /* * 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. */ static inline void __lru_add_drain_all(bool force_all_cpus) { … } void lru_add_drain_all(void) { … } #else void lru_add_drain_all(void) { lru_add_drain(); } #endif /* CONFIG_SMP */ atomic_t lru_disable_count = …; /* * lru_cache_disable() needs to be called before we start compiling * a list of pages to be migrated using isolate_lru_page(). * It drains pages 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) { … } /** * 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. * * 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. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ void folios_put_refs(struct folio_batch *folios, unsigned int *refs) { … } EXPORT_SYMBOL(…); /** * release_pages - batched put_page() * @arg: array of pages to release * @nr: number of pages * * 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 release_pages(release_pages_arg arg, int nr) { … } EXPORT_SYMBOL(…); /* * 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 __folio_batch_release(struct folio_batch *fbatch) { … } EXPORT_SYMBOL(…); /** * folio_batch_remove_exceptionals() - Prune non-folios from a batch. * @fbatch: The batch to prune * * 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. */ void folio_batch_remove_exceptionals(struct folio_batch *fbatch) { … } /* * Perform any setup for the swap system */ void __init swap_setup(void) { … }