mm/vmscan.c

// SPDX-License-Identifier: GPL-2.0
/*
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  Swap reorganised 29.12.95, Stephen Tweedie.
 *  kswapd added: 7.1.96  sct
 *  Removed kswapd_ctl limits, and swap out as many pages as needed
 *  to bring the system back to freepages.high: 2.4.97, Rik van Riel.
 *  Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com).
 *  Multiqueue VM started 5.8.00, Rik van Riel.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/module.h>
#include <linux/gfp.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/vmpressure.h>
#include <linux/vmstat.h>
#include <linux/file.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>	/* for buffer_heads_over_limit */
#include <linux/mm_inline.h>
#include <linux/backing-dev.h>
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/compaction.h>
#include <linux/notifier.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/memcontrol.h>
#include <linux/migrate.h>
#include <linux/delayacct.h>
#include <linux/sysctl.h>
#include <linux/memory-tiers.h>
#include <linux/oom.h>
#include <linux/pagevec.h>
#include <linux/prefetch.h>
#include <linux/printk.h>
#include <linux/dax.h>
#include <linux/psi.h>
#include <linux/pagewalk.h>
#include <linux/shmem_fs.h>
#include <linux/ctype.h>
#include <linux/debugfs.h>
#include <linux/khugepaged.h>
#include <linux/rculist_nulls.h>
#include <linux/random.h>

#include <asm/tlbflush.h>
#include <asm/div64.h>

#include <linux/swapops.h>
#include <linux/balloon_compaction.h>
#include <linux/sched/sysctl.h>

#include "internal.h"
#include "swap.h"

#define CREATE_TRACE_POINTS
#include <trace/events/vmscan.h>

struct scan_control {
	/* How many pages shrink_list() should reclaim */
	unsigned long nr_to_reclaim;

	/*
	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
	 * are scanned.
	 */
	nodemask_t	*nodemask;

	/*
	 * The memory cgroup that hit its limit and as a result is the
	 * primary target of this reclaim invocation.
	 */
	struct mem_cgroup *target_mem_cgroup;

	/*
	 * Scan pressure balancing between anon and file LRUs
	 */
	unsigned long	anon_cost;
	unsigned long	file_cost;

	/* Can active folios be deactivated as part of reclaim? */
#define DEACTIVATE_ANON 1
#define DEACTIVATE_FILE 2
	unsigned int may_deactivate:2;
	unsigned int force_deactivate:1;
	unsigned int skipped_deactivate:1;

	/* Writepage batching in laptop mode; RECLAIM_WRITE */
	unsigned int may_writepage:1;

	/* Can mapped folios be reclaimed? */
	unsigned int may_unmap:1;

	/* Can folios be swapped as part of reclaim? */
	unsigned int may_swap:1;

	/* Not allow cache_trim_mode to be turned on as part of reclaim? */
	unsigned int no_cache_trim_mode:1;

	/* Has cache_trim_mode failed at least once? */
	unsigned int cache_trim_mode_failed:1;

	/* Proactive reclaim invoked by userspace through memory.reclaim */
	unsigned int proactive:1;

	/*
	 * Cgroup memory below memory.low is protected as long as we
	 * don't threaten to OOM. If any cgroup is reclaimed at
	 * reduced force or passed over entirely due to its memory.low
	 * setting (memcg_low_skipped), and nothing is reclaimed as a
	 * result, then go back for one more cycle that reclaims the protected
	 * memory (memcg_low_reclaim) to avert OOM.
	 */
	unsigned int memcg_low_reclaim:1;
	unsigned int memcg_low_skipped:1;

	unsigned int hibernation_mode:1;

	/* One of the zones is ready for compaction */
	unsigned int compaction_ready:1;

	/* There is easily reclaimable cold cache in the current node */
	unsigned int cache_trim_mode:1;

	/* The file folios on the current node are dangerously low */
	unsigned int file_is_tiny:1;

	/* Always discard instead of demoting to lower tier memory */
	unsigned int no_demotion:1;

	/* Allocation order */
	s8 order;

	/* Scan (total_size >> priority) pages at once */
	s8 priority;

	/* The highest zone to isolate folios for reclaim from */
	s8 reclaim_idx;

	/* This context's GFP mask */
	gfp_t gfp_mask;

	/* Incremented by the number of inactive pages that were scanned */
	unsigned long nr_scanned;

	/* Number of pages freed so far during a call to shrink_zones() */
	unsigned long nr_reclaimed;

	struct {
		unsigned int dirty;
		unsigned int unqueued_dirty;
		unsigned int congested;
		unsigned int writeback;
		unsigned int immediate;
		unsigned int file_taken;
		unsigned int taken;
	} nr;

	/* for recording the reclaimed slab by now */
	struct reclaim_state reclaim_state;
};

#ifdef ARCH_HAS_PREFETCHW
#define prefetchw_prev_lru_folio(_folio, _base, _field)			\
	do {								\
		if ((_folio)->lru.prev != _base) {			\
			struct folio *prev;				\
									\
			prev = lru_to_folio(&(_folio->lru));		\
			prefetchw(&prev->_field);			\
		}							\
	} while (0)
#else
#define prefetchw_prev_lru_folio(_folio, _base, _field) do { } while (0)
#endif

/*
 * From 0 .. 200.  Higher means more swappy.
 */
int vm_swappiness = 60;

#ifdef CONFIG_MEMCG

/* Returns true for reclaim through cgroup limits or cgroup interfaces. */
static bool cgroup_reclaim(struct scan_control *sc)
{
	return sc->target_mem_cgroup;
}

/*
 * Returns true for reclaim on the root cgroup. This is true for direct
 * allocator reclaim and reclaim through cgroup interfaces on the root cgroup.
 */
static bool root_reclaim(struct scan_control *sc)
{
	return !sc->target_mem_cgroup || mem_cgroup_is_root(sc->target_mem_cgroup);
}

/**
 * writeback_throttling_sane - is the usual dirty throttling mechanism available?
 * @sc: scan_control in question
 *
 * The normal page dirty throttling mechanism in balance_dirty_pages() is
 * completely broken with the legacy memcg and direct stalling in
 * shrink_folio_list() is used for throttling instead, which lacks all the
 * niceties such as fairness, adaptive pausing, bandwidth proportional
 * allocation and configurability.
 *
 * This function tests whether the vmscan currently in progress can assume
 * that the normal dirty throttling mechanism is operational.
 */
static bool writeback_throttling_sane(struct scan_control *sc)
{
	if (!cgroup_reclaim(sc))
		return true;
#ifdef CONFIG_CGROUP_WRITEBACK
	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
		return true;
#endif
	return false;
}
#else
static bool cgroup_reclaim(struct scan_control *sc)
{
	return false;
}

static bool root_reclaim(struct scan_control *sc)
{
	return true;
}

static bool writeback_throttling_sane(struct scan_control *sc)
{
	return true;
}
#endif

static void set_task_reclaim_state(struct task_struct *task,
				   struct reclaim_state *rs)
{
	/* Check for an overwrite */
	WARN_ON_ONCE(rs && task->reclaim_state);

	/* Check for the nulling of an already-nulled member */
	WARN_ON_ONCE(!rs && !task->reclaim_state);

	task->reclaim_state = rs;
}

/*
 * flush_reclaim_state(): add pages reclaimed outside of LRU-based reclaim to
 * scan_control->nr_reclaimed.
 */
static void flush_reclaim_state(struct scan_control *sc)
{
	/*
	 * Currently, reclaim_state->reclaimed includes three types of pages
	 * freed outside of vmscan:
	 * (1) Slab pages.
	 * (2) Clean file pages from pruned inodes (on highmem systems).
	 * (3) XFS freed buffer pages.
	 *
	 * For all of these cases, we cannot universally link the pages to a
	 * single memcg. For example, a memcg-aware shrinker can free one object
	 * charged to the target memcg, causing an entire page to be freed.
	 * If we count the entire page as reclaimed from the memcg, we end up
	 * overestimating the reclaimed amount (potentially under-reclaiming).
	 *
	 * Only count such pages for global reclaim to prevent under-reclaiming
	 * from the target memcg; preventing unnecessary retries during memcg
	 * charging and false positives from proactive reclaim.
	 *
	 * For uncommon cases where the freed pages were actually mostly
	 * charged to the target memcg, we end up underestimating the reclaimed
	 * amount. This should be fine. The freed pages will be uncharged
	 * anyway, even if they are not counted here properly, and we will be
	 * able to make forward progress in charging (which is usually in a
	 * retry loop).
	 *
	 * We can go one step further, and report the uncharged objcg pages in
	 * memcg reclaim, to make reporting more accurate and reduce
	 * underestimation, but it's probably not worth the complexity for now.
	 */
	if (current->reclaim_state && root_reclaim(sc)) {
		sc->nr_reclaimed += current->reclaim_state->reclaimed;
		current->reclaim_state->reclaimed = 0;
	}
}

static bool can_demote(int nid, struct scan_control *sc)
{
	if (!numa_demotion_enabled)
		return false;
	if (sc && sc->no_demotion)
		return false;
	if (next_demotion_node(nid) == NUMA_NO_NODE)
		return false;

	return true;
}

static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
					  int nid,
					  struct scan_control *sc)
{
	if (memcg == NULL) {
		/*
		 * For non-memcg reclaim, is there
		 * space in any swap device?
		 */
		if (get_nr_swap_pages() > 0)
			return true;
	} else {
		/* Is the memcg below its swap limit? */
		if (mem_cgroup_get_nr_swap_pages(memcg) > 0)
			return true;
	}

	/*
	 * The page can not be swapped.
	 *
	 * Can it be reclaimed from this node via demotion?
	 */
	return can_demote(nid, sc);
}

/*
 * This misses isolated folios which are not accounted for to save counters.
 * As the data only determines if reclaim or compaction continues, it is
 * not expected that isolated folios will be a dominating factor.
 */
unsigned long zone_reclaimable_pages(struct zone *zone)
{
	unsigned long nr;

	nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) +
		zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE);
	if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL))
		nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) +
			zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON);

	return nr;
}

/**
 * lruvec_lru_size -  Returns the number of pages on the given LRU list.
 * @lruvec: lru vector
 * @lru: lru to use
 * @zone_idx: zones to consider (use MAX_NR_ZONES - 1 for the whole LRU list)
 */
static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru,
				     int zone_idx)
{
	unsigned long size = 0;
	int zid;

	for (zid = 0; zid <= zone_idx; zid++) {
		struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid];

		if (!managed_zone(zone))
			continue;

		if (!mem_cgroup_disabled())
			size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid);
		else
			size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru);
	}
	return size;
}

static unsigned long drop_slab_node(int nid)
{
	unsigned long freed = 0;
	struct mem_cgroup *memcg = NULL;

	memcg = mem_cgroup_iter(NULL, NULL, NULL);
	do {
		freed += shrink_slab(GFP_KERNEL, nid, memcg, 0);
	} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);

	return freed;
}

void drop_slab(void)
{
	int nid;
	int shift = 0;
	unsigned long freed;

	do {
		freed = 0;
		for_each_online_node(nid) {
			if (fatal_signal_pending(current))
				return;

			freed += drop_slab_node(nid);
		}
	} while ((freed >> shift++) > 1);
}

static int reclaimer_offset(void)
{
	BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
			PGDEMOTE_DIRECT - PGDEMOTE_KSWAPD);
	BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD !=
			PGDEMOTE_KHUGEPAGED - PGDEMOTE_KSWAPD);
	BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
			PGSCAN_DIRECT - PGSCAN_KSWAPD);
	BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD !=
			PGSCAN_KHUGEPAGED - PGSCAN_KSWAPD);

	if (current_is_kswapd())
		return 0;
	if (current_is_khugepaged())
		return PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD;
	return PGSTEAL_DIRECT - PGSTEAL_KSWAPD;
}

static inline int is_page_cache_freeable(struct folio *folio)
{
	/*
	 * A freeable page cache folio is referenced only by the caller
	 * that isolated the folio, the page cache and optional filesystem
	 * private data at folio->private.
	 */
	return folio_ref_count(folio) - folio_test_private(folio) ==
		1 + folio_nr_pages(folio);
}

/*
 * We detected a synchronous write error writing a folio out.  Probably
 * -ENOSPC.  We need to propagate that into the address_space for a subsequent
 * fsync(), msync() or close().
 *
 * The tricky part is that after writepage we cannot touch the mapping: nothing
 * prevents it from being freed up.  But we have a ref on the folio and once
 * that folio is locked, the mapping is pinned.
 *
 * We're allowed to run sleeping folio_lock() here because we know the caller has
 * __GFP_FS.
 */
static void handle_write_error(struct address_space *mapping,
				struct folio *folio, int error)
{
	folio_lock(folio);
	if (folio_mapping(folio) == mapping)
		mapping_set_error(mapping, error);
	folio_unlock(folio);
}

static bool skip_throttle_noprogress(pg_data_t *pgdat)
{
	int reclaimable = 0, write_pending = 0;
	int i;

	/*
	 * If kswapd is disabled, reschedule if necessary but do not
	 * throttle as the system is likely near OOM.
	 */
	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
		return true;

	/*
	 * If there are a lot of dirty/writeback folios then do not
	 * throttle as throttling will occur when the folios cycle
	 * towards the end of the LRU if still under writeback.
	 */
	for (i = 0; i < MAX_NR_ZONES; i++) {
		struct zone *zone = pgdat->node_zones + i;

		if (!managed_zone(zone))
			continue;

		reclaimable += zone_reclaimable_pages(zone);
		write_pending += zone_page_state_snapshot(zone,
						  NR_ZONE_WRITE_PENDING);
	}
	if (2 * write_pending <= reclaimable)
		return true;

	return false;
}

void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason)
{
	wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason];
	long timeout, ret;
	DEFINE_WAIT(wait);

	/*
	 * Do not throttle user workers, kthreads other than kswapd or
	 * workqueues. They may be required for reclaim to make
	 * forward progress (e.g. journalling workqueues or kthreads).
	 */
	if (!current_is_kswapd() &&
	    current->flags & (PF_USER_WORKER|PF_KTHREAD)) {
		cond_resched();
		return;
	}

	/*
	 * These figures are pulled out of thin air.
	 * VMSCAN_THROTTLE_ISOLATED is a transient condition based on too many
	 * parallel reclaimers which is a short-lived event so the timeout is
	 * short. Failing to make progress or waiting on writeback are
	 * potentially long-lived events so use a longer timeout. This is shaky
	 * logic as a failure to make progress could be due to anything from
	 * writeback to a slow device to excessive referenced folios at the tail
	 * of the inactive LRU.
	 */
	switch(reason) {
	case VMSCAN_THROTTLE_WRITEBACK:
		timeout = HZ/10;

		if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) {
			WRITE_ONCE(pgdat->nr_reclaim_start,
				node_page_state(pgdat, NR_THROTTLED_WRITTEN));
		}

		break;
	case VMSCAN_THROTTLE_CONGESTED:
		fallthrough;
	case VMSCAN_THROTTLE_NOPROGRESS:
		if (skip_throttle_noprogress(pgdat)) {
			cond_resched();
			return;
		}

		timeout = 1;

		break;
	case VMSCAN_THROTTLE_ISOLATED:
		timeout = HZ/50;
		break;
	default:
		WARN_ON_ONCE(1);
		timeout = HZ;
		break;
	}

	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
	ret = schedule_timeout(timeout);
	finish_wait(wqh, &wait);

	if (reason == VMSCAN_THROTTLE_WRITEBACK)
		atomic_dec(&pgdat->nr_writeback_throttled);

	trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout),
				jiffies_to_usecs(timeout - ret),
				reason);
}

/*
 * Account for folios written if tasks are throttled waiting on dirty
 * folios to clean. If enough folios have been cleaned since throttling
 * started then wakeup the throttled tasks.
 */
void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio,
							int nr_throttled)
{
	unsigned long nr_written;

	node_stat_add_folio(folio, NR_THROTTLED_WRITTEN);

	/*
	 * This is an inaccurate read as the per-cpu deltas may not
	 * be synchronised. However, given that the system is
	 * writeback throttled, it is not worth taking the penalty
	 * of getting an accurate count. At worst, the throttle
	 * timeout guarantees forward progress.
	 */
	nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) -
		READ_ONCE(pgdat->nr_reclaim_start);

	if (nr_written > SWAP_CLUSTER_MAX * nr_throttled)
		wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]);
}

/* possible outcome of pageout() */
typedef enum {
	/* failed to write folio out, folio is locked */
	PAGE_KEEP,
	/* move folio to the active list, folio is locked */
	PAGE_ACTIVATE,
	/* folio has been sent to the disk successfully, folio is unlocked */
	PAGE_SUCCESS,
	/* folio is clean and locked */
	PAGE_CLEAN,
} pageout_t;

/*
 * pageout is called by shrink_folio_list() for each dirty folio.
 * Calls ->writepage().
 */
static pageout_t pageout(struct folio *folio, struct address_space *mapping,
			 struct swap_iocb **plug)
{
	/*
	 * If the folio is dirty, only perform writeback if that write
	 * will be non-blocking.  To prevent this allocation from being
	 * stalled by pagecache activity.  But note that there may be
	 * stalls if we need to run get_block().  We could test
	 * PagePrivate for that.
	 *
	 * If this process is currently in __generic_file_write_iter() against
	 * this folio's queue, we can perform writeback even if that
	 * will block.
	 *
	 * If the folio is swapcache, write it back even if that would
	 * block, for some throttling. This happens by accident, because
	 * swap_backing_dev_info is bust: it doesn't reflect the
	 * congestion state of the swapdevs.  Easy to fix, if needed.
	 */
	if (!is_page_cache_freeable(folio))
		return PAGE_KEEP;
	if (!mapping) {
		/*
		 * Some data journaling orphaned folios can have
		 * folio->mapping == NULL while being dirty with clean buffers.
		 */
		if (folio_test_private(folio)) {
			if (try_to_free_buffers(folio)) {
				folio_clear_dirty(folio);
				pr_info("%s: orphaned folio\n", __func__);
				return PAGE_CLEAN;
			}
		}
		return PAGE_KEEP;
	}
	if (mapping->a_ops->writepage == NULL)
		return PAGE_ACTIVATE;

	if (folio_clear_dirty_for_io(folio)) {
		int res;
		struct writeback_control wbc = {
			.sync_mode = WB_SYNC_NONE,
			.nr_to_write = SWAP_CLUSTER_MAX,
			.range_start = 0,
			.range_end = LLONG_MAX,
			.for_reclaim = 1,
			.swap_plug = plug,
		};

		folio_set_reclaim(folio);
		res = mapping->a_ops->writepage(&folio->page, &wbc);
		if (res < 0)
			handle_write_error(mapping, folio, res);
		if (res == AOP_WRITEPAGE_ACTIVATE) {
			folio_clear_reclaim(folio);
			return PAGE_ACTIVATE;
		}

		if (!folio_test_writeback(folio)) {
			/* synchronous write or broken a_ops? */
			folio_clear_reclaim(folio);
		}
		trace_mm_vmscan_write_folio(folio);
		node_stat_add_folio(folio, NR_VMSCAN_WRITE);
		return PAGE_SUCCESS;
	}

	return PAGE_CLEAN;
}

/*
 * Same as remove_mapping, but if the folio is removed from the mapping, it
 * gets returned with a refcount of 0.
 */
static int __remove_mapping(struct address_space *mapping, struct folio *folio,
			    bool reclaimed, struct mem_cgroup *target_memcg)
{
	int refcount;
	void *shadow = NULL;

	BUG_ON(!folio_test_locked(folio));
	BUG_ON(mapping != folio_mapping(folio));

	if (!folio_test_swapcache(folio))
		spin_lock(&mapping->host->i_lock);
	xa_lock_irq(&mapping->i_pages);
	/*
	 * The non racy check for a busy folio.
	 *
	 * Must be careful with the order of the tests. When someone has
	 * a ref to the folio, it may be possible that they dirty it then
	 * drop the reference. So if the dirty flag is tested before the
	 * refcount here, then the following race may occur:
	 *
	 * get_user_pages(&page);
	 * [user mapping goes away]
	 * write_to(page);
	 *				!folio_test_dirty(folio)    [good]
	 * folio_set_dirty(folio);
	 * folio_put(folio);
	 *				!refcount(folio)   [good, discard it]
	 *
	 * [oops, our write_to data is lost]
	 *
	 * Reversing the order of the tests ensures such a situation cannot
	 * escape unnoticed. The smp_rmb is needed to ensure the folio->flags
	 * load is not satisfied before that of folio->_refcount.
	 *
	 * Note that if the dirty flag is always set via folio_mark_dirty,
	 * and thus under the i_pages lock, then this ordering is not required.
	 */
	refcount = 1 + folio_nr_pages(folio);
	if (!folio_ref_freeze(folio, refcount))
		goto cannot_free;
	/* note: atomic_cmpxchg in folio_ref_freeze provides the smp_rmb */
	if (unlikely(folio_test_dirty(folio))) {
		folio_ref_unfreeze(folio, refcount);
		goto cannot_free;
	}

	if (folio_test_swapcache(folio)) {
		swp_entry_t swap = folio->swap;

		if (reclaimed && !mapping_exiting(mapping))
			shadow = workingset_eviction(folio, target_memcg);
		__delete_from_swap_cache(folio, swap, shadow);
		mem_cgroup_swapout(folio, swap);
		xa_unlock_irq(&mapping->i_pages);
		put_swap_folio(folio, swap);
	} else {
		void (*free_folio)(struct folio *);

		free_folio = mapping->a_ops->free_folio;
		/*
		 * Remember a shadow entry for reclaimed file cache in
		 * order to detect refaults, thus thrashing, later on.
		 *
		 * But don't store shadows in an address space that is
		 * already exiting.  This is not just an optimization,
		 * inode reclaim needs to empty out the radix tree or
		 * the nodes are lost.  Don't plant shadows behind its
		 * back.
		 *
		 * We also don't store shadows for DAX mappings because the
		 * only page cache folios found in these are zero pages
		 * covering holes, and because we don't want to mix DAX
		 * exceptional entries and shadow exceptional entries in the
		 * same address_space.
		 */
		if (reclaimed && folio_is_file_lru(folio) &&
		    !mapping_exiting(mapping) && !dax_mapping(mapping))
			shadow = workingset_eviction(folio, target_memcg);
		__filemap_remove_folio(folio, shadow);
		xa_unlock_irq(&mapping->i_pages);
		if (mapping_shrinkable(mapping))
			inode_add_lru(mapping->host);
		spin_unlock(&mapping->host->i_lock);

		if (free_folio)
			free_folio(folio);
	}

	return 1;

cannot_free:
	xa_unlock_irq(&mapping->i_pages);
	if (!folio_test_swapcache(folio))
		spin_unlock(&mapping->host->i_lock);
	return 0;
}

/**
 * remove_mapping() - Attempt to remove a folio from its mapping.
 * @mapping: The address space.
 * @folio: The folio to remove.
 *
 * If the folio is dirty, under writeback or if someone else has a ref
 * on it, removal will fail.
 * Return: The number of pages removed from the mapping.  0 if the folio
 * could not be removed.
 * Context: The caller should have a single refcount on the folio and
 * hold its lock.
 */
long remove_mapping(struct address_space *mapping, struct folio *folio)
{
	if (__remove_mapping(mapping, folio, false, NULL)) {
		/*
		 * Unfreezing the refcount with 1 effectively
		 * drops the pagecache ref for us without requiring another
		 * atomic operation.
		 */
		folio_ref_unfreeze(folio, 1);
		return folio_nr_pages(folio);
	}
	return 0;
}

/**
 * folio_putback_lru - Put previously isolated folio onto appropriate LRU list.
 * @folio: Folio to be returned to an LRU list.
 *
 * Add previously isolated @folio to appropriate LRU list.
 * The folio may still be unevictable for other reasons.
 *
 * Context: lru_lock must not be held, interrupts must be enabled.
 */
void folio_putback_lru(struct folio *folio)
{
	folio_add_lru(folio);
	folio_put(folio);		/* drop ref from isolate */
}

enum folio_references {
	FOLIOREF_RECLAIM,
	FOLIOREF_RECLAIM_CLEAN,
	FOLIOREF_KEEP,
	FOLIOREF_ACTIVATE,
};

static enum folio_references folio_check_references(struct folio *folio,
						  struct scan_control *sc)
{
	int referenced_ptes, referenced_folio;
	unsigned long vm_flags;

	referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup,
					   &vm_flags);
	referenced_folio = folio_test_clear_referenced(folio);

	/*
	 * The supposedly reclaimable folio was found to be in a VM_LOCKED vma.
	 * Let the folio, now marked Mlocked, be moved to the unevictable list.
	 */
	if (vm_flags & VM_LOCKED)
		return FOLIOREF_ACTIVATE;

	/* rmap lock contention: rotate */
	if (referenced_ptes == -1)
		return FOLIOREF_KEEP;

	if (referenced_ptes) {
		/*
		 * All mapped folios start out with page table
		 * references from the instantiating fault, so we need
		 * to look twice if a mapped file/anon folio is used more
		 * than once.
		 *
		 * Mark it and spare it for another trip around the
		 * inactive list.  Another page table reference will
		 * lead to its activation.
		 *
		 * Note: the mark is set for activated folios as well
		 * so that recently deactivated but used folios are
		 * quickly recovered.
		 */
		folio_set_referenced(folio);

		if (referenced_folio || referenced_ptes > 1)
			return FOLIOREF_ACTIVATE;

		/*
		 * Activate file-backed executable folios after first usage.
		 */
		if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio))
			return FOLIOREF_ACTIVATE;

		return FOLIOREF_KEEP;
	}

	/* Reclaim if clean, defer dirty folios to writeback */
	if (referenced_folio && folio_is_file_lru(folio))
		return FOLIOREF_RECLAIM_CLEAN;

	return FOLIOREF_RECLAIM;
}

/* Check if a folio is dirty or under writeback */
static void folio_check_dirty_writeback(struct folio *folio,
				       bool *dirty, bool *writeback)
{
	struct address_space *mapping;

	/*
	 * Anonymous folios are not handled by flushers and must be written
	 * from reclaim context. Do not stall reclaim based on them.
	 * MADV_FREE anonymous folios are put into inactive file list too.
	 * They could be mistakenly treated as file lru. So further anon
	 * test is needed.
	 */
	if (!folio_is_file_lru(folio) ||
	    (folio_test_anon(folio) && !folio_test_swapbacked(folio))) {
		*dirty = false;
		*writeback = false;
		return;
	}

	/* By default assume that the folio flags are accurate */
	*dirty = folio_test_dirty(folio);
	*writeback = folio_test_writeback(folio);

	/* Verify dirty/writeback state if the filesystem supports it */
	if (!folio_test_private(folio))
		return;

	mapping = folio_mapping(folio);
	if (mapping && mapping->a_ops->is_dirty_writeback)
		mapping->a_ops->is_dirty_writeback(folio, dirty, writeback);
}

static struct folio *alloc_demote_folio(struct folio *src,
		unsigned long private)
{
	struct folio *dst;
	nodemask_t *allowed_mask;
	struct migration_target_control *mtc;

	mtc = (struct migration_target_control *)private;

	allowed_mask = mtc->nmask;
	/*
	 * make sure we allocate from the target node first also trying to
	 * demote or reclaim pages from the target node via kswapd if we are
	 * low on free memory on target node. If we don't do this and if
	 * we have free memory on the slower(lower) memtier, we would start
	 * allocating pages from slower(lower) memory tiers without even forcing
	 * a demotion of cold pages from the target memtier. This can result
	 * in the kernel placing hot pages in slower(lower) memory tiers.
	 */
	mtc->nmask = NULL;
	mtc->gfp_mask |= __GFP_THISNODE;
	dst = alloc_migration_target(src, (unsigned long)mtc);
	if (dst)
		return dst;

	mtc->gfp_mask &= ~__GFP_THISNODE;
	mtc->nmask = allowed_mask;

	return alloc_migration_target(src, (unsigned long)mtc);
}

/*
 * Take folios on @demote_folios and attempt to demote them to another node.
 * Folios which are not demoted are left on @demote_folios.
 */
static unsigned int demote_folio_list(struct list_head *demote_folios,
				     struct pglist_data *pgdat)
{
	int target_nid = next_demotion_node(pgdat->node_id);
	unsigned int nr_succeeded;
	nodemask_t allowed_mask;

	struct migration_target_control mtc = {
		/*
		 * Allocate from 'node', or fail quickly and quietly.
		 * When this happens, 'page' will likely just be discarded
		 * instead of migrated.
		 */
		.gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) | __GFP_NOWARN |
			__GFP_NOMEMALLOC | GFP_NOWAIT,
		.nid = target_nid,
		.nmask = &allowed_mask,
		.reason = MR_DEMOTION,
	};

	if (list_empty(demote_folios))
		return 0;

	if (target_nid == NUMA_NO_NODE)
		return 0;

	node_get_allowed_targets(pgdat, &allowed_mask);

	/* Demotion ignores all cpuset and mempolicy settings */
	migrate_pages(demote_folios, alloc_demote_folio, NULL,
		      (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION,
		      &nr_succeeded);

	mod_node_page_state(pgdat, PGDEMOTE_KSWAPD + reclaimer_offset(),
			    nr_succeeded);

	return nr_succeeded;
}

static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask)
{
	if (gfp_mask & __GFP_FS)
		return true;
	if (!folio_test_swapcache(folio) || !(gfp_mask & __GFP_IO))
		return false;
	/*
	 * We can "enter_fs" for swap-cache with only __GFP_IO
	 * providing this isn't SWP_FS_OPS.
	 * ->flags can be updated non-atomicially (scan_swap_map_slots),
	 * but that will never affect SWP_FS_OPS, so the data_race
	 * is safe.
	 */
	return !data_race(folio_swap_flags(folio) & SWP_FS_OPS);
}

/*
 * shrink_folio_list() returns the number of reclaimed pages
 */
static unsigned int shrink_folio_list(struct list_head *folio_list,
		struct pglist_data *pgdat, struct scan_control *sc,
		struct reclaim_stat *stat, bool ignore_references)
{
	struct folio_batch free_folios;
	LIST_HEAD(ret_folios);
	LIST_HEAD(demote_folios);
	unsigned int nr_reclaimed = 0;
	unsigned int pgactivate = 0;
	bool do_demote_pass;
	struct swap_iocb *plug = NULL;

	folio_batch_init(&free_folios);
	memset(stat, 0, sizeof(*stat));
	cond_resched();
	do_demote_pass = can_demote(pgdat->node_id, sc);

retry:
	while (!list_empty(folio_list)) {
		struct address_space *mapping;
		struct folio *folio;
		enum folio_references references = FOLIOREF_RECLAIM;
		bool dirty, writeback;
		unsigned int nr_pages;

		cond_resched();

		folio = lru_to_folio(folio_list);
		list_del(&folio->lru);

		if (!folio_trylock(folio))
			goto keep;

		VM_BUG_ON_FOLIO(folio_test_active(folio), folio);

		nr_pages = folio_nr_pages(folio);

		/* Account the number of base pages */
		sc->nr_scanned += nr_pages;

		if (unlikely(!folio_evictable(folio)))
			goto activate_locked;

		if (!sc->may_unmap && folio_mapped(folio))
			goto keep_locked;

		/* folio_update_gen() tried to promote this page? */
		if (lru_gen_enabled() && !ignore_references &&
		    folio_mapped(folio) && folio_test_referenced(folio))
			goto keep_locked;

		/*
		 * The number of dirty pages determines if a node is marked
		 * reclaim_congested. kswapd will stall and start writing
		 * folios if the tail of the LRU is all dirty unqueued folios.
		 */
		folio_check_dirty_writeback(folio, &dirty, &writeback);
		if (dirty || writeback)
			stat->nr_dirty += nr_pages;

		if (dirty && !writeback)
			stat->nr_unqueued_dirty += nr_pages;

		/*
		 * Treat this folio as congested if folios are cycling
		 * through the LRU so quickly that the folios marked
		 * for immediate reclaim are making it to the end of
		 * the LRU a second time.
		 */
		if (writeback && folio_test_reclaim(folio))
			stat->nr_congested += nr_pages;

		/*
		 * If a folio at the tail of the LRU is under writeback, there
		 * are three cases to consider.
		 *
		 * 1) If reclaim is encountering an excessive number
		 *    of folios under writeback and this folio has both
		 *    the writeback and reclaim flags set, then it
		 *    indicates that folios are being queued for I/O but
		 *    are being recycled through the LRU before the I/O
		 *    can complete. Waiting on the folio itself risks an
		 *    indefinite stall if it is impossible to writeback
		 *    the folio due to I/O error or disconnected storage
		 *    so instead note that the LRU is being scanned too
		 *    quickly and the caller can stall after the folio
		 *    list has been processed.
		 *
		 * 2) Global or new memcg reclaim encounters a folio that is
		 *    not marked for immediate reclaim, or the caller does not
		 *    have __GFP_FS (or __GFP_IO if it's simply going to swap,
		 *    not to fs). In this case mark the folio for immediate
		 *    reclaim and continue scanning.
		 *
		 *    Require may_enter_fs() because we would wait on fs, which
		 *    may not have submitted I/O yet. And the loop driver might
		 *    enter reclaim, and deadlock if it waits on a folio for
		 *    which it is needed to do the write (loop masks off
		 *    __GFP_IO|__GFP_FS for this reason); but more thought
		 *    would probably show more reasons.
		 *
		 * 3) Legacy memcg encounters a folio that already has the
		 *    reclaim flag set. memcg does not have any dirty folio
		 *    throttling so we could easily OOM just because too many
		 *    folios are in writeback and there is nothing else to
		 *    reclaim. Wait for the writeback to complete.
		 *
		 * In cases 1) and 2) we activate the folios to get them out of
		 * the way while we continue scanning for clean folios on the
		 * inactive list and refilling from the active list. The
		 * observation here is that waiting for disk writes is more
		 * expensive than potentially causing reloads down the line.
		 * Since they're marked for immediate reclaim, they won't put
		 * memory pressure on the cache working set any longer than it
		 * takes to write them to disk.
		 */
		if (folio_test_writeback(folio)) {
			/* Case 1 above */
			if (current_is_kswapd() &&
			    folio_test_reclaim(folio) &&
			    test_bit(PGDAT_WRITEBACK, &pgdat->flags)) {
				stat->nr_immediate += nr_pages;
				goto activate_locked;

			/* Case 2 above */
			} else if (writeback_throttling_sane(sc) ||
			    !folio_test_reclaim(folio) ||
			    !may_enter_fs(folio, sc->gfp_mask)) {
				/*
				 * This is slightly racy -
				 * folio_end_writeback() might have
				 * just cleared the reclaim flag, then
				 * setting the reclaim flag here ends up
				 * interpreted as the readahead flag - but
				 * that does not matter enough to care.
				 * What we do want is for this folio to
				 * have the reclaim flag set next time
				 * memcg reclaim reaches the tests above,
				 * so it will then wait for writeback to
				 * avoid OOM; and it's also appropriate
				 * in global reclaim.
				 */
				folio_set_reclaim(folio);
				stat->nr_writeback += nr_pages;
				goto activate_locked;

			/* Case 3 above */
			} else {
				folio_unlock(folio);
				folio_wait_writeback(folio);
				/* then go back and try same folio again */
				list_add_tail(&folio->lru, folio_list);
				continue;
			}
		}

		if (!ignore_references)
			references = folio_check_references(folio, sc);

		switch (references) {
		case FOLIOREF_ACTIVATE:
			goto activate_locked;
		case FOLIOREF_KEEP:
			stat->nr_ref_keep += nr_pages;
			goto keep_locked;
		case FOLIOREF_RECLAIM:
		case FOLIOREF_RECLAIM_CLEAN:
			; /* try to reclaim the folio below */
		}

		/*
		 * Before reclaiming the folio, try to relocate
		 * its contents to another node.
		 */
		if (do_demote_pass &&
		    (thp_migration_supported() || !folio_test_large(folio))) {
			list_add(&folio->lru, &demote_folios);
			folio_unlock(folio);
			continue;
		}

		/*
		 * Anonymous process memory has backing store?
		 * Try to allocate it some swap space here.
		 * Lazyfree folio could be freed directly
		 */
		if (folio_test_anon(folio) && folio_test_swapbacked(folio)) {
			if (!folio_test_swapcache(folio)) {
				if (!(sc->gfp_mask & __GFP_IO))
					goto keep_locked;
				if (folio_maybe_dma_pinned(folio))
					goto keep_locked;
				if (folio_test_large(folio)) {
					/* cannot split folio, skip it */
					if (!can_split_folio(folio, NULL))
						goto activate_locked;
					/*
					 * Split partially mapped folios right away.
					 * We can free the unmapped pages without IO.
					 */
					if (data_race(!list_empty(&folio->_deferred_list)) &&
					    split_folio_to_list(folio, folio_list))
						goto activate_locked;
				}
				if (!add_to_swap(folio)) {
					int __maybe_unused order = folio_order(folio);

					if (!folio_test_large(folio))
						goto activate_locked_split;
					/* Fallback to swap normal pages */
					if (split_folio_to_list(folio, folio_list))
						goto activate_locked;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
					if (nr_pages >= HPAGE_PMD_NR) {
						count_memcg_folio_events(folio,
							THP_SWPOUT_FALLBACK, 1);
						count_vm_event(THP_SWPOUT_FALLBACK);
					}
					count_mthp_stat(order, MTHP_STAT_ANON_SWPOUT_FALLBACK);
#endif
					if (!add_to_swap(folio))
						goto activate_locked_split;
				}
			}
		} else if (folio_test_swapbacked(folio) &&
			   folio_test_large(folio)) {
			/* Split shmem folio */
			if (split_folio_to_list(folio, folio_list))
				goto keep_locked;
		}

		/*
		 * If the folio was split above, the tail pages will make
		 * their own pass through this function and be accounted
		 * then.
		 */
		if ((nr_pages > 1) && !folio_test_large(folio)) {
			sc->nr_scanned -= (nr_pages - 1);
			nr_pages = 1;
		}

		/*
		 * The folio is mapped into the page tables of one or more
		 * processes. Try to unmap it here.
		 */
		if (folio_mapped(folio)) {
			enum ttu_flags flags = TTU_BATCH_FLUSH;
			bool was_swapbacked = folio_test_swapbacked(folio);

			if (folio_test_pmd_mappable(folio))
				flags |= TTU_SPLIT_HUGE_PMD;
			/*
			 * Without TTU_SYNC, try_to_unmap will only begin to
			 * hold PTL from the first present PTE within a large
			 * folio. Some initial PTEs might be skipped due to
			 * races with parallel PTE writes in which PTEs can be
			 * cleared temporarily before being written new present
			 * values. This will lead to a large folio is still
			 * mapped while some subpages have been partially
			 * unmapped after try_to_unmap; TTU_SYNC helps
			 * try_to_unmap acquire PTL from the first PTE,
			 * eliminating the influence of temporary PTE values.
			 */
			if (folio_test_large(folio) && list_empty(&folio->_deferred_list))
				flags |= TTU_SYNC;

			try_to_unmap(folio, flags);
			if (folio_mapped(folio)) {
				stat->nr_unmap_fail += nr_pages;
				if (!was_swapbacked &&
				    folio_test_swapbacked(folio))
					stat->nr_lazyfree_fail += nr_pages;
				goto activate_locked;
			}
		}

		/*
		 * Folio is unmapped now so it cannot be newly pinned anymore.
		 * No point in trying to reclaim folio if it is pinned.
		 * Furthermore we don't want to reclaim underlying fs metadata
		 * if the folio is pinned and thus potentially modified by the
		 * pinning process as that may upset the filesystem.
		 */
		if (folio_maybe_dma_pinned(folio))
			goto activate_locked;

		mapping = folio_mapping(folio);
		if (folio_test_dirty(folio)) {
			/*
			 * Only kswapd can writeback filesystem folios
			 * to avoid risk of stack overflow. But avoid
			 * injecting inefficient single-folio I/O into
			 * flusher writeback as much as possible: only
			 * write folios when we've encountered many
			 * dirty folios, and when we've already scanned
			 * the rest of the LRU for clean folios and see
			 * the same dirty folios again (with the reclaim
			 * flag set).
			 */
			if (folio_is_file_lru(folio) &&
			    (!current_is_kswapd() ||
			     !folio_test_reclaim(folio) ||
			     !test_bit(PGDAT_DIRTY, &pgdat->flags))) {
				/*
				 * Immediately reclaim when written back.
				 * Similar in principle to folio_deactivate()
				 * except we already have the folio isolated
				 * and know it's dirty
				 */
				node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE,
						nr_pages);
				folio_set_reclaim(folio);

				goto activate_locked;
			}

			if (references == FOLIOREF_RECLAIM_CLEAN)
				goto keep_locked;
			if (!may_enter_fs(folio, sc->gfp_mask))
				goto keep_locked;
			if (!sc->may_writepage)
				goto keep_locked;

			/*
			 * Folio is dirty. Flush the TLB if a writable entry
			 * potentially exists to avoid CPU writes after I/O
			 * starts and then write it out here.
			 */
			try_to_unmap_flush_dirty();
			switch (pageout(folio, mapping, &plug)) {
			case PAGE_KEEP:
				goto keep_locked;
			case PAGE_ACTIVATE:
				goto activate_locked;
			case PAGE_SUCCESS:
				stat->nr_pageout += nr_pages;

				if (folio_test_writeback(folio))
					goto keep;
				if (folio_test_dirty(folio))
					goto keep;

				/*
				 * A synchronous write - probably a ramdisk.  Go
				 * ahead and try to reclaim the folio.
				 */
				if (!folio_trylock(folio))
					goto keep;
				if (folio_test_dirty(folio) ||
				    folio_test_writeback(folio))
					goto keep_locked;
				mapping = folio_mapping(folio);
				fallthrough;
			case PAGE_CLEAN:
				; /* try to free the folio below */
			}
		}

		/*
		 * If the folio has buffers, try to free the buffer
		 * mappings associated with this folio. If we succeed
		 * we try to free the folio as well.
		 *
		 * We do this even if the folio is dirty.
		 * filemap_release_folio() does not perform I/O, but it
		 * is possible for a folio to have the dirty flag set,
		 * but it is actually clean (all its buffers are clean).
		 * This happens if the buffers were written out directly,
		 * with submit_bh(). ext3 will do this, as well as
		 * the blockdev mapping.  filemap_release_folio() will
		 * discover that cleanness and will drop the buffers
		 * and mark the folio clean - it can be freed.
		 *
		 * Rarely, folios can have buffers and no ->mapping.
		 * These are the folios which were not successfully
		 * invalidated in truncate_cleanup_folio().  We try to
		 * drop those buffers here and if that worked, and the
		 * folio is no longer mapped into process address space
		 * (refcount == 1) it can be freed.  Otherwise, leave
		 * the folio on the LRU so it is swappable.
		 */
		if (folio_needs_release(folio)) {
			if (!filemap_release_folio(folio, sc->gfp_mask))
				goto activate_locked;
			if (!mapping && folio_ref_count(folio) == 1) {
				folio_unlock(folio);
				if (folio_put_testzero(folio))
					goto free_it;
				else {
					/*
					 * rare race with speculative reference.
					 * the speculative reference will free
					 * this folio shortly, so we may
					 * increment nr_reclaimed here (and
					 * leave it off the LRU).
					 */
					nr_reclaimed += nr_pages;
					continue;
				}
			}
		}

		if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) {
			/* follow __remove_mapping for reference */
			if (!folio_ref_freeze(folio, 1))
				goto keep_locked;
			/*
			 * The folio has only one reference left, which is
			 * from the isolation. After the caller puts the
			 * folio back on the lru and drops the reference, the
			 * folio will be freed anyway. It doesn't matter
			 * which lru it goes on. So we don't bother checking
			 * the dirty flag here.
			 */
			count_vm_events(PGLAZYFREED, nr_pages);
			count_memcg_folio_events(folio, PGLAZYFREED, nr_pages);
		} else if (!mapping || !__remove_mapping(mapping, folio, true,
							 sc->target_mem_cgroup))
			goto keep_locked;

		folio_unlock(folio);
free_it:
		/*
		 * Folio may get swapped out as a whole, need to account
		 * all pages in it.
		 */
		nr_reclaimed += nr_pages;

		if (folio_test_large(folio) &&
		    folio_test_large_rmappable(folio))
			folio_undo_large_rmappable(folio);
		if (folio_batch_add(&free_folios, folio) == 0) {
			mem_cgroup_uncharge_folios(&free_folios);
			try_to_unmap_flush();
			free_unref_folios(&free_folios);
		}
		continue;

activate_locked_split:
		/*
		 * The tail pages that are failed to add into swap cache
		 * reach here.  Fixup nr_scanned and nr_pages.
		 */
		if (nr_pages > 1) {
			sc->nr_scanned -= (nr_pages - 1);
			nr_pages = 1;
		}
activate_locked:
		/* Not a candidate for swapping, so reclaim swap space. */
		if (folio_test_swapcache(folio) &&
		    (mem_cgroup_swap_full(folio) || folio_test_mlocked(folio)))
			folio_free_swap(folio);
		VM_BUG_ON_FOLIO(folio_test_active(folio), folio);
		if (!folio_test_mlocked(folio)) {
			int type = folio_is_file_lru(folio);
			folio_set_active(folio);
			stat->nr_activate[type] += nr_pages;
			count_memcg_folio_events(folio, PGACTIVATE, nr_pages);
		}
keep_locked:
		folio_unlock(folio);
keep:
		list_add(&folio->lru, &ret_folios);
		VM_BUG_ON_FOLIO(folio_test_lru(folio) ||
				folio_test_unevictable(folio), folio);
	}
	/* 'folio_list' is always empty here */

	/* Migrate folios selected for demotion */
	nr_reclaimed += demote_folio_list(&demote_folios, pgdat);
	/* Folios that could not be demoted are still in @demote_folios */
	if (!list_empty(&demote_folios)) {
		/* Folios which weren't demoted go back on @folio_list */
		list_splice_init(&demote_folios, folio_list);

		/*
		 * goto retry to reclaim the undemoted folios in folio_list if
		 * desired.
		 *
		 * Reclaiming directly from top tier nodes is not often desired
		 * due to it breaking the LRU ordering: in general memory
		 * should be reclaimed from lower tier nodes and demoted from
		 * top tier nodes.
		 *
		 * However, disabling reclaim from top tier nodes entirely
		 * would cause ooms in edge scenarios where lower tier memory
		 * is unreclaimable for whatever reason, eg memory being
		 * mlocked or too hot to reclaim. We can disable reclaim
		 * from top tier nodes in proactive reclaim though as that is
		 * not real memory pressure.
		 */
		if (!sc->proactive) {
			do_demote_pass = false;
			goto retry;
		}
	}

	pgactivate = stat->nr_activate[0] + stat->nr_activate[1];

	mem_cgroup_uncharge_folios(&free_folios);
	try_to_unmap_flush();
	free_unref_folios(&free_folios);

	list_splice(&ret_folios, folio_list);
	count_vm_events(PGACTIVATE, pgactivate);

	if (plug)
		swap_write_unplug(plug);
	return nr_reclaimed;
}

unsigned int reclaim_clean_pages_from_list(struct zone *zone,
					   struct list_head *folio_list)
{
	struct scan_control sc = {
		.gfp_mask = GFP_KERNEL,
		.may_unmap = 1,
	};
	struct reclaim_stat stat;
	unsigned int nr_reclaimed;
	struct folio *folio, *next;
	LIST_HEAD(clean_folios);
	unsigned int noreclaim_flag;

	list_for_each_entry_safe(folio, next, folio_list, lru) {
		if (!folio_test_hugetlb(folio) && folio_is_file_lru(folio) &&
		    !folio_test_dirty(folio) && !__folio_test_movable(folio) &&
		    !folio_test_unevictable(folio)) {
			folio_clear_active(folio);
			list_move(&folio->lru, &clean_folios);
		}
	}

	/*
	 * We should be safe here since we are only dealing with file pages and
	 * we are not kswapd and therefore cannot write dirty file pages. But
	 * call memalloc_noreclaim_save() anyway, just in case these conditions
	 * change in the future.
	 */
	noreclaim_flag = memalloc_noreclaim_save();
	nr_reclaimed = shrink_folio_list(&clean_folios, zone->zone_pgdat, &sc,
					&stat, true);
	memalloc_noreclaim_restore(noreclaim_flag);

	list_splice(&clean_folios, folio_list);
	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
			    -(long)nr_reclaimed);
	/*
	 * Since lazyfree pages are isolated from file LRU from the beginning,
	 * they will rotate back to anonymous LRU in the end if it failed to
	 * discard so isolated count will be mismatched.
	 * Compensate the isolated count for both LRU lists.
	 */
	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON,
			    stat.nr_lazyfree_fail);
	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
			    -(long)stat.nr_lazyfree_fail);
	return nr_reclaimed;
}

/*
 * Update LRU sizes after isolating pages. The LRU size updates must
 * be complete before mem_cgroup_update_lru_size due to a sanity check.
 */
static __always_inline void update_lru_sizes(struct lruvec *lruvec,
			enum lru_list lru, unsigned long *nr_zone_taken)
{
	int zid;

	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
		if (!nr_zone_taken[zid])
			continue;

		update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);
	}

}

#ifdef CONFIG_CMA
/*
 * It is waste of effort to scan and reclaim CMA pages if it is not available
 * for current allocation context. Kswapd can not be enrolled as it can not
 * distinguish this scenario by using sc->gfp_mask = GFP_KERNEL
 */
static bool skip_cma(struct folio *folio, struct scan_control *sc)
{
	return !current_is_kswapd() &&
			gfp_migratetype(sc->gfp_mask) != MIGRATE_MOVABLE &&
			folio_migratetype(folio) == MIGRATE_CMA;
}
#else
static bool skip_cma(struct folio *folio, struct scan_control *sc)
{
	return false;
}
#endif

/*
 * Isolating page from the lruvec to fill in @dst list by nr_to_scan times.
 *
 * lruvec->lru_lock is heavily contended.  Some of the functions that
 * shrink the lists perform better by taking out a batch of pages
 * and working on them outside the LRU lock.
 *
 * For pagecache intensive workloads, this function is the hottest
 * spot in the kernel (apart from copy_*_user functions).
 *
 * Lru_lock must be held before calling this function.
 *
 * @nr_to_scan:	The number of eligible pages to look through on the list.
 * @lruvec:	The LRU vector to pull pages from.
 * @dst:	The temp list to put pages on to.
 * @nr_scanned:	The number of pages that were scanned.
 * @sc:		The scan_control struct for this reclaim session
 * @lru:	LRU list id for isolating
 *
 * returns how many pages were moved onto *@dst.
 */
static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
		struct lruvec *lruvec, struct list_head *dst,
		unsigned long *nr_scanned, struct scan_control *sc,
		enum lru_list lru)
{
	struct list_head *src = &lruvec->lists[lru];
	unsigned long nr_taken = 0;
	unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
	unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
	unsigned long skipped = 0;
	unsigned long scan, total_scan, nr_pages;
	LIST_HEAD(folios_skipped);

	total_scan = 0;
	scan = 0;
	while (scan < nr_to_scan && !list_empty(src)) {
		struct list_head *move_to = src;
		struct folio *folio;

		folio = lru_to_folio(src);
		prefetchw_prev_lru_folio(folio, src, flags);

		nr_pages = folio_nr_pages(folio);
		total_scan += nr_pages;

		if (folio_zonenum(folio) > sc->reclaim_idx ||
				skip_cma(folio, sc)) {
			nr_skipped[folio_zonenum(folio)] += nr_pages;
			move_to = &folios_skipped;
			goto move;
		}

		/*
		 * Do not count skipped folios because that makes the function
		 * return with no isolated folios if the LRU mostly contains
		 * ineligible folios.  This causes the VM to not reclaim any
		 * folios, triggering a premature OOM.
		 * Account all pages in a folio.
		 */
		scan += nr_pages;

		if (!folio_test_lru(folio))
			goto move;
		if (!sc->may_unmap && folio_mapped(folio))
			goto move;

		/*
		 * Be careful not to clear the lru flag until after we're
		 * sure the folio is not being freed elsewhere -- the
		 * folio release code relies on it.
		 */
		if (unlikely(!folio_try_get(folio)))
			goto move;

		if (!folio_test_clear_lru(folio)) {
			/* Another thread is already isolating this folio */
			folio_put(folio);
			goto move;
		}

		nr_taken += nr_pages;
		nr_zone_taken[folio_zonenum(folio)] += nr_pages;
		move_to = dst;
move:
		list_move(&folio->lru, move_to);
	}

	/*
	 * Splice any skipped folios to the start of the LRU list. Note that
	 * this disrupts the LRU order when reclaiming for lower zones but
	 * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX
	 * scanning would soon rescan the same folios to skip and waste lots
	 * of cpu cycles.
	 */
	if (!list_empty(&folios_skipped)) {
		int zid;

		list_splice(&folios_skipped, src);
		for (zid = 0; zid < MAX_NR_ZONES; zid++) {
			if (!nr_skipped[zid])
				continue;

			__count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
			skipped += nr_skipped[zid];
		}
	}
	*nr_scanned = total_scan;
	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
				    total_scan, skipped, nr_taken, lru);
	update_lru_sizes(lruvec, lru, nr_zone_taken);
	return nr_taken;
}

/**
 * folio_isolate_lru() - Try to isolate a folio from its LRU list.
 * @folio: Folio to isolate from its LRU list.
 *
 * Isolate a @folio from an LRU list and adjust the vmstat statistic
 * corresponding to whatever LRU list the folio was on.
 *
 * The folio will have its LRU flag cleared.  If it was found on the
 * active list, it will have the Active flag set.  If it was found on the
 * unevictable list, it will have the Unevictable flag set.  These flags
 * may need to be cleared by the caller before letting the page go.
 *
 * Context:
 *
 * (1) Must be called with an elevated refcount on the folio. This is a
 *     fundamental difference from isolate_lru_folios() (which is called
 *     without a stable reference).
 * (2) The lru_lock must not be held.
 * (3) Interrupts must be enabled.
 *
 * Return: true if the folio was removed from an LRU list.
 * false if the folio was not on an LRU list.
 */
bool folio_isolate_lru(struct folio *folio)
{
	bool ret = false;

	VM_BUG_ON_FOLIO(!folio_ref_count(folio), folio);

	if (folio_test_clear_lru(folio)) {
		struct lruvec *lruvec;

		folio_get(folio);
		lruvec = folio_lruvec_lock_irq(folio);
		lruvec_del_folio(lruvec, folio);
		unlock_page_lruvec_irq(lruvec);
		ret = true;
	}

	return ret;
}

/*
 * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and
 * then get rescheduled. When there are massive number of tasks doing page
 * allocation, such sleeping direct reclaimers may keep piling up on each CPU,
 * the LRU list will go small and be scanned faster than necessary, leading to
 * unnecessary swapping, thrashing and OOM.
 */
static bool too_many_isolated(struct pglist_data *pgdat, int file,
		struct scan_control *sc)
{
	unsigned long inactive, isolated;
	bool too_many;

	if (current_is_kswapd())
		return false;

	if (!writeback_throttling_sane(sc))
		return false;

	if (file) {
		inactive = node_page_state(pgdat, NR_INACTIVE_FILE);
		isolated = node_page_state(pgdat, NR_ISOLATED_FILE);
	} else {
		inactive = node_page_state(pgdat, NR_INACTIVE_ANON);
		isolated = node_page_state(pgdat, NR_ISOLATED_ANON);
	}

	/*
	 * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they
	 * won't get blocked by normal direct-reclaimers, forming a circular
	 * deadlock.
	 */
	if (gfp_has_io_fs(sc->gfp_mask))
		inactive >>= 3;

	too_many = isolated > inactive;

	/* Wake up tasks throttled due to too_many_isolated. */
	if (!too_many)
		wake_throttle_isolated(pgdat);

	return too_many;
}

/*
 * move_folios_to_lru() moves folios from private @list to appropriate LRU list.
 *
 * Returns the number of pages moved to the given lruvec.
 */
static unsigned int move_folios_to_lru(struct lruvec *lruvec,
		struct list_head *list)
{
	int nr_pages, nr_moved = 0;
	struct folio_batch free_folios;

	folio_batch_init(&free_folios);
	while (!list_empty(list)) {
		struct folio *folio = lru_to_folio(list);

		VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
		list_del(&folio->lru);
		if (unlikely(!folio_evictable(folio))) {
			spin_unlock_irq(&lruvec->lru_lock);
			folio_putback_lru(folio);
			spin_lock_irq(&lruvec->lru_lock);
			continue;
		}

		/*
		 * The folio_set_lru needs to be kept here for list integrity.
		 * Otherwise:
		 *   #0 move_folios_to_lru             #1 release_pages
		 *   if (!folio_put_testzero())
		 *				      if (folio_put_testzero())
		 *				        !lru //skip lru_lock
		 *     folio_set_lru()
		 *     list_add(&folio->lru,)
		 *                                        list_add(&folio->lru,)
		 */
		folio_set_lru(folio);

		if (unlikely(folio_put_testzero(folio))) {
			__folio_clear_lru_flags(folio);

			if (folio_test_large(folio) &&
			    folio_test_large_rmappable(folio))
				folio_undo_large_rmappable(folio);
			if (folio_batch_add(&free_folios, folio) == 0) {
				spin_unlock_irq(&lruvec->lru_lock);
				mem_cgroup_uncharge_folios(&free_folios);
				free_unref_folios(&free_folios);
				spin_lock_irq(&lruvec->lru_lock);
			}

			continue;
		}

		/*
		 * All pages were isolated from the same lruvec (and isolation
		 * inhibits memcg migration).
		 */
		VM_BUG_ON_FOLIO(!folio_matches_lruvec(folio, lruvec), folio);
		lruvec_add_folio(lruvec, folio);
		nr_pages = folio_nr_pages(folio);
		nr_moved += nr_pages;
		if (folio_test_active(folio))
			workingset_age_nonresident(lruvec, nr_pages);
	}

	if (free_folios.nr) {
		spin_unlock_irq(&lruvec->lru_lock);
		mem_cgroup_uncharge_folios(&free_folios);
		free_unref_folios(&free_folios);
		spin_lock_irq(&lruvec->lru_lock);
	}

	return nr_moved;
}

/*
 * If a kernel thread (such as nfsd for loop-back mounts) services a backing
 * device by writing to the page cache it sets PF_LOCAL_THROTTLE. In this case
 * we should not throttle.  Otherwise it is safe to do so.
 */
static int current_may_throttle(void)
{
	return !(current->flags & PF_LOCAL_THROTTLE);
}

/*
 * shrink_inactive_list() is a helper for shrink_node().  It returns the number
 * of reclaimed pages
 */
static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
		struct lruvec *lruvec, struct scan_control *sc,
		enum lru_list lru)
{
	LIST_HEAD(folio_list);
	unsigned long nr_scanned;
	unsigned int nr_reclaimed = 0;
	unsigned long nr_taken;
	struct reclaim_stat stat;
	bool file = is_file_lru(lru);
	enum vm_event_item item;
	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
	bool stalled = false;

	while (unlikely(too_many_isolated(pgdat, file, sc))) {
		if (stalled)
			return 0;

		/* wait a bit for the reclaimer. */
		stalled = true;
		reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED);

		/* We are about to die and free our memory. Return now. */
		if (fatal_signal_pending(current))
			return SWAP_CLUSTER_MAX;
	}

	lru_add_drain();

	spin_lock_irq(&lruvec->lru_lock);

	nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &folio_list,
				     &nr_scanned, sc, lru);

	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
	item = PGSCAN_KSWAPD + reclaimer_offset();
	if (!cgroup_reclaim(sc))
		__count_vm_events(item, nr_scanned);
	__count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned);
	__count_vm_events(PGSCAN_ANON + file, nr_scanned);

	spin_unlock_irq(&lruvec->lru_lock);

	if (nr_taken == 0)
		return 0;

	nr_reclaimed = shrink_folio_list(&folio_list, pgdat, sc, &stat, false);

	spin_lock_irq(&lruvec->lru_lock);
	move_folios_to_lru(lruvec, &folio_list);

	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
	item = PGSTEAL_KSWAPD + reclaimer_offset();
	if (!cgroup_reclaim(sc))
		__count_vm_events(item, nr_reclaimed);
	__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
	__count_vm_events(PGSTEAL_ANON + file, nr_reclaimed);
	spin_unlock_irq(&lruvec->lru_lock);

	lru_note_cost(lruvec, file, stat.nr_pageout, nr_scanned - nr_reclaimed);

	/*
	 * If dirty folios are scanned that are not queued for IO, it
	 * implies that flushers are not doing their job. This can
	 * happen when memory pressure pushes dirty folios to the end of
	 * the LRU before the dirty limits are breached and the dirty
	 * data has expired. It can also happen when the proportion of
	 * dirty folios grows not through writes but through memory
	 * pressure reclaiming all the clean cache. And in some cases,
	 * the flushers simply cannot keep up with the allocation
	 * rate. Nudge the flusher threads in case they are asleep.
	 */
	if (stat.nr_unqueued_dirty == nr_taken) {
		wakeup_flusher_threads(WB_REASON_VMSCAN);
		/*
		 * For cgroupv1 dirty throttling is achieved by waking up
		 * the kernel flusher here and later waiting on folios
		 * which are in writeback to finish (see shrink_folio_list()).
		 *
		 * Flusher may not be able to issue writeback quickly
		 * enough for cgroupv1 writeback throttling to work
		 * on a large system.
		 */
		if (!writeback_throttling_sane(sc))
			reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
	}

	sc->nr.dirty += stat.nr_dirty;
	sc->nr.congested += stat.nr_congested;
	sc->nr.unqueued_dirty += stat.nr_unqueued_dirty;
	sc->nr.writeback += stat.nr_writeback;
	sc->nr.immediate += stat.nr_immediate;
	sc->nr.taken += nr_taken;
	if (file)
		sc->nr.file_taken += nr_taken;

	trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
			nr_scanned, nr_reclaimed, &stat, sc->priority, file);
	return nr_reclaimed;
}

/*
 * shrink_active_list() moves folios from the active LRU to the inactive LRU.
 *
 * We move them the other way if the folio is referenced by one or more
 * processes.
 *
 * If the folios are mostly unmapped, the processing is fast and it is
 * appropriate to hold lru_lock across the whole operation.  But if
 * the folios are mapped, the processing is slow (folio_referenced()), so
 * we should drop lru_lock around each folio.  It's impossible to balance
 * this, so instead we remove the folios from the LRU while processing them.
 * It is safe to rely on the active flag against the non-LRU folios in here
 * because nobody will play with that bit on a non-LRU folio.
 *
 * The downside is that we have to touch folio->_refcount against each folio.
 * But we had to alter folio->flags anyway.
 */
static void shrink_active_list(unsigned long nr_to_scan,
			       struct lruvec *lruvec,
			       struct scan_control *sc,
			       enum lru_list lru)
{
	unsigned long nr_taken;
	unsigned long nr_scanned;
	unsigned long vm_flags;
	LIST_HEAD(l_hold);	/* The folios which were snipped off */
	LIST_HEAD(l_active);
	LIST_HEAD(l_inactive);
	unsigned nr_deactivate, nr_activate;
	unsigned nr_rotated = 0;
	bool file = is_file_lru(lru);
	struct pglist_data *pgdat = lruvec_pgdat(lruvec);

	lru_add_drain();

	spin_lock_irq(&lruvec->lru_lock);

	nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &l_hold,
				     &nr_scanned, sc, lru);

	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);

	if (!cgroup_reclaim(sc))
		__count_vm_events(PGREFILL, nr_scanned);
	__count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned);

	spin_unlock_irq(&lruvec->lru_lock);

	while (!list_empty(&l_hold)) {
		struct folio *folio;

		cond_resched();
		folio = lru_to_folio(&l_hold);
		list_del(&folio->lru);

		if (unlikely(!folio_evictable(folio))) {
			folio_putback_lru(folio);
			continue;
		}

		if (unlikely(buffer_heads_over_limit)) {
			if (folio_needs_release(folio) &&
			    folio_trylock(folio)) {
				filemap_release_folio(folio, 0);
				folio_unlock(folio);
			}
		}

		/* Referenced or rmap lock contention: rotate */
		if (folio_referenced(folio, 0, sc->target_mem_cgroup,
				     &vm_flags) != 0) {
			/*
			 * Identify referenced, file-backed active folios and
			 * give them one more trip around the active list. So
			 * that executable code get better chances to stay in
			 * memory under moderate memory pressure.  Anon folios
			 * are not likely to be evicted by use-once streaming
			 * IO, plus JVM can create lots of anon VM_EXEC folios,
			 * so we ignore them here.
			 */
			if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) {
				nr_rotated += folio_nr_pages(folio);
				list_add(&folio->lru, &l_active);
				continue;
			}
		}

		folio_clear_active(folio);	/* we are de-activating */
		folio_set_workingset(folio);
		list_add(&folio->lru, &l_inactive);
	}

	/*
	 * Move folios back to the lru list.
	 */
	spin_lock_irq(&lruvec->lru_lock);

	nr_activate = move_folios_to_lru(lruvec, &l_active);
	nr_deactivate = move_folios_to_lru(lruvec, &l_inactive);

	__count_vm_events(PGDEACTIVATE, nr_deactivate);
	__count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate);

	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
	spin_unlock_irq(&lruvec->lru_lock);

	if (nr_rotated)
		lru_note_cost(lruvec, file, 0, nr_rotated);
	trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate,
			nr_deactivate, nr_rotated, sc->priority, file);
}

static unsigned int reclaim_folio_list(struct list_head *folio_list,
				      struct pglist_data *pgdat)
{
	struct reclaim_stat dummy_stat;
	unsigned int nr_reclaimed;
	struct folio *folio;
	struct scan_control sc = {
		.gfp_mask = GFP_KERNEL,
		.may_writepage = 1,
		.may_unmap = 1,
		.may_swap = 1,
		.no_demotion = 1,
	};

	nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &dummy_stat, true);
	while (!list_empty(folio_list)) {
		folio = lru_to_folio(folio_list);
		list_del(&folio->lru);
		folio_putback_lru(folio);
	}

	return nr_reclaimed;
}

unsigned long reclaim_pages(struct list_head *folio_list)
{
	int nid;
	unsigned int nr_reclaimed = 0;
	LIST_HEAD(node_folio_list);
	unsigned int noreclaim_flag;

	if (list_empty(folio_list))
		return nr_reclaimed;

	noreclaim_flag = memalloc_noreclaim_save();

	nid = folio_nid(lru_to_folio(folio_list));
	do {
		struct folio *folio = lru_to_folio(folio_list);

		if (nid == folio_nid(folio)) {
			folio_clear_active(folio);
			list_move(&folio->lru, &node_folio_list);
			continue;
		}

		nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
		nid = folio_nid(lru_to_folio(folio_list));
	} while (!list_empty(folio_list));

	nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));

	memalloc_noreclaim_restore(noreclaim_flag);

	return nr_reclaimed;
}

static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
				 struct lruvec *lruvec, struct scan_control *sc)
{
	if (is_active_lru(lru)) {
		if (sc->may_deactivate & (1 << is_file_lru(lru)))
			shrink_active_list(nr_to_scan, lruvec, sc, lru);
		else
			sc->skipped_deactivate = 1;
		return 0;
	}

	return shrink_inactive_list(nr_to_scan, lruvec, sc, lru);
}

/*
 * The inactive anon list should be small enough that the VM never has
 * to do too much work.
 *
 * The inactive file list should be small enough to leave most memory
 * to the established workingset on the scan-resistant active list,
 * but large enough to avoid thrashing the aggregate readahead window.
 *
 * Both inactive lists should also be large enough that each inactive
 * folio has a chance to be referenced again before it is reclaimed.
 *
 * If that fails and refaulting is observed, the inactive list grows.
 *
 * The inactive_ratio is the target ratio of ACTIVE to INACTIVE folios
 * on this LRU, maintained by the pageout code. An inactive_ratio
 * of 3 means 3:1 or 25% of the folios are kept on the inactive list.
 *
 * total     target    max
 * memory    ratio     inactive
 * -------------------------------------
 *   10MB       1         5MB
 *  100MB       1        50MB
 *    1GB       3       250MB
 *   10GB      10       0.9GB
 *  100GB      31         3GB
 *    1TB     101        10GB
 *   10TB     320        32GB
 */
static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru)
{
	enum lru_list active_lru = inactive_lru + LRU_ACTIVE;
	unsigned long inactive, active;
	unsigned long inactive_ratio;
	unsigned long gb;

	inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru);
	active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru);

	gb = (inactive + active) >> (30 - PAGE_SHIFT);
	if (gb)
		inactive_ratio = int_sqrt(10 * gb);
	else
		inactive_ratio = 1;

	return inactive * inactive_ratio < active;
}

enum scan_balance {
	SCAN_EQUAL,
	SCAN_FRACT,
	SCAN_ANON,
	SCAN_FILE,
};

static void prepare_scan_control(pg_data_t *pgdat, struct scan_control *sc)
{
	unsigned long file;
	struct lruvec *target_lruvec;

	if (lru_gen_enabled())
		return;

	target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);

	/*
	 * Flush the memory cgroup stats, so that we read accurate per-memcg
	 * lruvec stats for heuristics.
	 */
	mem_cgroup_flush_stats(sc->target_mem_cgroup);

	/*
	 * Determine the scan balance between anon and file LRUs.
	 */
	spin_lock_irq(&target_lruvec->lru_lock);
	sc->anon_cost = target_lruvec->anon_cost;
	sc->file_cost = target_lruvec->file_cost;
	spin_unlock_irq(&target_lruvec->lru_lock);

	/*
	 * Target desirable inactive:active list ratios for the anon
	 * and file LRU lists.
	 */
	if (!sc->force_deactivate) {
		unsigned long refaults;

		/*
		 * When refaults are being observed, it means a new
		 * workingset is being established. Deactivate to get
		 * rid of any stale active pages quickly.
		 */
		refaults = lruvec_page_state(target_lruvec,
				WORKINGSET_ACTIVATE_ANON);
		if (refaults != target_lruvec->refaults[WORKINGSET_ANON] ||
			inactive_is_low(target_lruvec, LRU_INACTIVE_ANON))
			sc->may_deactivate |= DEACTIVATE_ANON;
		else
			sc->may_deactivate &= ~DEACTIVATE_ANON;

		refaults = lruvec_page_state(target_lruvec,
				WORKINGSET_ACTIVATE_FILE);
		if (refaults != target_lruvec->refaults[WORKINGSET_FILE] ||
		    inactive_is_low(target_lruvec, LRU_INACTIVE_FILE))
			sc->may_deactivate |= DEACTIVATE_FILE;
		else
			sc->may_deactivate &= ~DEACTIVATE_FILE;
	} else
		sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE;

	/*
	 * If we have plenty of inactive file pages that aren't
	 * thrashing, try to reclaim those first before touching
	 * anonymous pages.
	 */
	file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE);
	if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE) &&
	    !sc->no_cache_trim_mode)
		sc->cache_trim_mode = 1;
	else
		sc->cache_trim_mode = 0;

	/*
	 * Prevent the reclaimer from falling into the cache trap: as
	 * cache pages start out inactive, every cache fault will tip
	 * the scan balance towards the file LRU.  And as the file LRU
	 * shrinks, so does the window for rotation from references.
	 * This means we have a runaway feedback loop where a tiny
	 * thrashing file LRU becomes infinitely more attractive than
	 * anon pages.  Try to detect this based on file LRU size.
	 */
	if (!cgroup_reclaim(sc)) {
		unsigned long total_high_wmark = 0;
		unsigned long free, anon;
		int z;

		free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES);
		file = node_page_state(pgdat, NR_ACTIVE_FILE) +
			   node_page_state(pgdat, NR_INACTIVE_FILE);

		for (z = 0; z < MAX_NR_ZONES; z++) {
			struct zone *zone = &pgdat->node_zones[z];

			if (!managed_zone(zone))
				continue;

			total_high_wmark += high_wmark_pages(zone);
		}

		/*
		 * Consider anon: if that's low too, this isn't a
		 * runaway file reclaim problem, but rather just
		 * extreme pressure. Reclaim as per usual then.
		 */
		anon = node_page_state(pgdat, NR_INACTIVE_ANON);

		sc->file_is_tiny =
			file + free <= total_high_wmark &&
			!(sc->may_deactivate & DEACTIVATE_ANON) &&
			anon >> sc->priority;
	}
}

/*
 * Determine how aggressively the anon and file LRU lists should be
 * scanned.
 *
 * nr[0] = anon inactive folios to scan; nr[1] = anon active folios to scan
 * nr[2] = file inactive folios to scan; nr[3] = file active folios to scan
 */
static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
			   unsigned long *nr)
{
	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
	unsigned long anon_cost, file_cost, total_cost;
	int swappiness = mem_cgroup_swappiness(memcg);
	u64 fraction[ANON_AND_FILE];
	u64 denominator = 0;	/* gcc */
	enum scan_balance scan_balance;
	unsigned long ap, fp;
	enum lru_list lru;

	/* If we have no swap space, do not bother scanning anon folios. */
	if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) {
		scan_balance = SCAN_FILE;
		goto out;
	}

	/*
	 * Global reclaim will swap to prevent OOM even with no
	 * swappiness, but memcg users want to use this knob to
	 * disable swapping for individual groups completely when
	 * using the memory controller's swap limit feature would be
	 * too expensive.
	 */
	if (cgroup_reclaim(sc) && !swappiness) {
		scan_balance = SCAN_FILE;
		goto out;
	}

	/*
	 * Do not apply any pressure balancing cleverness when the
	 * system is close to OOM, scan both anon and file equally
	 * (unless the swappiness setting disagrees with swapping).
	 */
	if (!sc->priority && swappiness) {
		scan_balance = SCAN_EQUAL;
		goto out;
	}

	/*
	 * If the system is almost out of file pages, force-scan anon.
	 */
	if (sc->file_is_tiny) {
		scan_balance = SCAN_ANON;
		goto out;
	}

	/*
	 * If there is enough inactive page cache, we do not reclaim
	 * anything from the anonymous working right now.
	 */
	if (sc->cache_trim_mode) {
		scan_balance = SCAN_FILE;
		goto out;
	}

	scan_balance = SCAN_FRACT;
	/*
	 * Calculate the pressure balance between anon and file pages.
	 *
	 * The amount of pressure we put on each LRU is inversely
	 * proportional to the cost of reclaiming each list, as
	 * determined by the share of pages that are refaulting, times
	 * the relative IO cost of bringing back a swapped out
	 * anonymous page vs reloading a filesystem page (swappiness).
	 *
	 * Although we limit that influence to ensure no list gets
	 * left behind completely: at least a third of the pressure is
	 * applied, before swappiness.
	 *
	 * With swappiness at 100, anon and file have equal IO cost.
	 */
	total_cost = sc->anon_cost + sc->file_cost;
	anon_cost = total_cost + sc->anon_cost;
	file_cost = total_cost + sc->file_cost;
	total_cost = anon_cost + file_cost;

	ap = swappiness * (total_cost + 1);
	ap /= anon_cost + 1;

	fp = (200 - swappiness) * (total_cost + 1);
	fp /= file_cost + 1;

	fraction[0] = ap;
	fraction[1] = fp;
	denominator = ap + fp;
out:
	for_each_evictable_lru(lru) {
		bool file = is_file_lru(lru);
		unsigned long lruvec_size;
		unsigned long low, min;
		unsigned long scan;

		lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
		mem_cgroup_protection(sc->target_mem_cgroup, memcg,
				      &min, &low);

		if (min || low) {
			/*
			 * Scale a cgroup's reclaim pressure by proportioning
			 * its current usage to its memory.low or memory.min
			 * setting.
			 *
			 * This is important, as otherwise scanning aggression
			 * becomes extremely binary -- from nothing as we
			 * approach the memory protection threshold, to totally
			 * nominal as we exceed it.  This results in requiring
			 * setting extremely liberal protection thresholds. It
			 * also means we simply get no protection at all if we
			 * set it too low, which is not ideal.
			 *
			 * If there is any protection in place, we reduce scan
			 * pressure by how much of the total memory used is
			 * within protection thresholds.
			 *
			 * There is one special case: in the first reclaim pass,
			 * we skip over all groups that are within their low
			 * protection. If that fails to reclaim enough pages to
			 * satisfy the reclaim goal, we come back and override
			 * the best-effort low protection. However, we still
			 * ideally want to honor how well-behaved groups are in
			 * that case instead of simply punishing them all
			 * equally. As such, we reclaim them based on how much
			 * memory they are using, reducing the scan pressure
			 * again by how much of the total memory used is under
			 * hard protection.
			 */
			unsigned long cgroup_size = mem_cgroup_size(memcg);
			unsigned long protection;

			/* memory.low scaling, make sure we retry before OOM */
			if (!sc->memcg_low_reclaim && low > min) {
				protection = low;
				sc->memcg_low_skipped = 1;
			} else {
				protection = min;
			}

			/* Avoid TOCTOU with earlier protection check */
			cgroup_size = max(cgroup_size, protection);

			scan = lruvec_size - lruvec_size * protection /
				(cgroup_size + 1);

			/*
			 * Minimally target SWAP_CLUSTER_MAX pages to keep
			 * reclaim moving forwards, avoiding decrementing
			 * sc->priority further than desirable.
			 */
			scan = max(scan, SWAP_CLUSTER_MAX);
		} else {
			scan = lruvec_size;
		}

		scan >>= sc->priority;

		/*
		 * If the cgroup's already been deleted, make sure to
		 * scrape out the remaining cache.
		 */
		if (!scan && !mem_cgroup_online(memcg))
			scan = min(lruvec_size, SWAP_CLUSTER_MAX);

		switch (scan_balance) {
		case SCAN_EQUAL:
			/* Scan lists relative to size */
			break;
		case SCAN_FRACT:
			/*
			 * Scan types proportional to swappiness and
			 * their relative recent reclaim efficiency.
			 * Make sure we don't miss the last page on
			 * the offlined memory cgroups because of a
			 * round-off error.
			 */
			scan = mem_cgroup_online(memcg) ?
			       div64_u64(scan * fraction[file], denominator) :
			       DIV64_U64_ROUND_UP(scan * fraction[file],
						  denominator);
			break;
		case SCAN_FILE:
		case SCAN_ANON:
			/* Scan one type exclusively */
			if ((scan_balance == SCAN_FILE) != file)
				scan = 0;
			break;
		default:
			/* Look ma, no brain */
			BUG();
		}

		nr[lru] = scan;
	}
}

/*
 * Anonymous LRU management is a waste if there is
 * ultimately no way to reclaim the memory.
 */
static bool can_age_anon_pages(struct pglist_data *pgdat,
			       struct scan_control *sc)
{
	/* Aging the anon LRU is valuable if swap is present: */
	if (total_swap_pages > 0)
		return true;

	/* Also valuable if anon pages can be demoted: */
	return can_demote(pgdat->node_id, sc);
}

#ifdef CONFIG_LRU_GEN

#ifdef CONFIG_LRU_GEN_ENABLED
DEFINE_STATIC_KEY_ARRAY_TRUE(lru_gen_caps, NR_LRU_GEN_CAPS);
#define get_cap(cap)	static_branch_likely(&lru_gen_caps[cap])
#else
DEFINE_STATIC_KEY_ARRAY_FALSE(lru_gen_caps, NR_LRU_GEN_CAPS);
#define get_cap(cap)	static_branch_unlikely(&lru_gen_caps[cap])
#endif

static bool should_walk_mmu(void)
{
	return arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK);
}

static bool should_clear_pmd_young(void)
{
	return arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG);
}

/******************************************************************************
 *                          shorthand helpers
 ******************************************************************************/

#define LRU_REFS_FLAGS	(BIT(PG_referenced) | BIT(PG_workingset))

#define DEFINE_MAX_SEQ(lruvec)						\
	unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq)

#define DEFINE_MIN_SEQ(lruvec)						\
	unsigned long min_seq[ANON_AND_FILE] = {			\
		READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_ANON]),	\
		READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_FILE]),	\
	}

#define for_each_gen_type_zone(gen, type, zone)				\
	for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++)			\
		for ((type) = 0; (type) < ANON_AND_FILE; (type)++)	\
			for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++)

#define get_memcg_gen(seq)	((seq) % MEMCG_NR_GENS)
#define get_memcg_bin(bin)	((bin) % MEMCG_NR_BINS)

static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid)
{
	struct pglist_data *pgdat = NODE_DATA(nid);

#ifdef CONFIG_MEMCG
	if (memcg) {
		struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec;

		/* see the comment in mem_cgroup_lruvec() */
		if (!lruvec->pgdat)
			lruvec->pgdat = pgdat;

		return lruvec;
	}
#endif
	VM_WARN_ON_ONCE(!mem_cgroup_disabled());

	return &pgdat->__lruvec;
}

static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc)
{
	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
	struct pglist_data *pgdat = lruvec_pgdat(lruvec);

	if (!sc->may_swap)
		return 0;

	if (!can_demote(pgdat->node_id, sc) &&
	    mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH)
		return 0;

	return mem_cgroup_swappiness(memcg);
}

static int get_nr_gens(struct lruvec *lruvec, int type)
{
	return lruvec->lrugen.max_seq - lruvec->lrugen.min_seq[type] + 1;
}

static bool __maybe_unused seq_is_valid(struct lruvec *lruvec)
{
	/* see the comment on lru_gen_folio */
	return get_nr_gens(lruvec, LRU_GEN_FILE) >= MIN_NR_GENS &&
	       get_nr_gens(lruvec, LRU_GEN_FILE) <= get_nr_gens(lruvec, LRU_GEN_ANON) &&
	       get_nr_gens(lruvec, LRU_GEN_ANON) <= MAX_NR_GENS;
}

/******************************************************************************
 *                          Bloom filters
 ******************************************************************************/

/*
 * Bloom filters with m=1<<15, k=2 and the false positive rates of ~1/5 when
 * n=10,000 and ~1/2 when n=20,000, where, conventionally, m is the number of
 * bits in a bitmap, k is the number of hash functions and n is the number of
 * inserted items.
 *
 * Page table walkers use one of the two filters to reduce their search space.
 * To get rid of non-leaf entries that no longer have enough leaf entries, the
 * aging uses the double-buffering technique to flip to the other filter each
 * time it produces a new generation. For non-leaf entries that have enough
 * leaf entries, the aging carries them over to the next generation in
 * walk_pmd_range(); the eviction also report them when walking the rmap
 * in lru_gen_look_around().
 *
 * For future optimizations:
 * 1. It's not necessary to keep both filters all the time. The spare one can be
 *    freed after the RCU grace period and reallocated if needed again.
 * 2. And when reallocating, it's worth scaling its size according to the number
 *    of inserted entries in the other filter, to reduce the memory overhead on
 *    small systems and false positives on large systems.
 * 3. Jenkins' hash function is an alternative to Knuth's.
 */
#define BLOOM_FILTER_SHIFT	15

static inline int filter_gen_from_seq(unsigned long seq)
{
	return seq % NR_BLOOM_FILTERS;
}

static void get_item_key(void *item, int *key)
{
	u32 hash = hash_ptr(item, BLOOM_FILTER_SHIFT * 2);

	BUILD_BUG_ON(BLOOM_FILTER_SHIFT * 2 > BITS_PER_TYPE(u32));

	key[0] = hash & (BIT(BLOOM_FILTER_SHIFT) - 1);
	key[1] = hash >> BLOOM_FILTER_SHIFT;
}

static bool test_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq,
			      void *item)
{
	int key[2];
	unsigned long *filter;
	int gen = filter_gen_from_seq(seq);

	filter = READ_ONCE(mm_state->filters[gen]);
	if (!filter)
		return true;

	get_item_key(item, key);

	return test_bit(key[0], filter) && test_bit(key[1], filter);
}

static void update_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq,
				void *item)
{
	int key[2];
	unsigned long *filter;
	int gen = filter_gen_from_seq(seq);

	filter = READ_ONCE(mm_state->filters[gen]);
	if (!filter)
		return;

	get_item_key(item, key);

	if (!test_bit(key[0], filter))
		set_bit(key[0], filter);
	if (!test_bit(key[1], filter))
		set_bit(key[1], filter);
}

static void reset_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq)
{
	unsigned long *filter;
	int gen = filter_gen_from_seq(seq);

	filter = mm_state->filters[gen];
	if (filter) {
		bitmap_clear(filter, 0, BIT(BLOOM_FILTER_SHIFT));
		return;
	}

	filter = bitmap_zalloc(BIT(BLOOM_FILTER_SHIFT),
			       __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN);
	WRITE_ONCE(mm_state->filters[gen], filter);
}

/******************************************************************************
 *                          mm_struct list
 ******************************************************************************/

#ifdef CONFIG_LRU_GEN_WALKS_MMU

static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg)
{
	static struct lru_gen_mm_list mm_list = {
		.fifo = LIST_HEAD_INIT(mm_list.fifo),
		.lock = __SPIN_LOCK_UNLOCKED(mm_list.lock),
	};

#ifdef CONFIG_MEMCG
	if (memcg)
		return &memcg->mm_list;
#endif
	VM_WARN_ON_ONCE(!mem_cgroup_disabled());

	return &mm_list;
}

static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec)
{
	return &lruvec->mm_state;
}

static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk)
{
	int key;
	struct mm_struct *mm;
	struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
	struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec);

	mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list);
	key = pgdat->node_id % BITS_PER_TYPE(mm->lru_gen.bitmap);

	if (!walk->force_scan && !test_bit(key, &mm->lru_gen.bitmap))
		return NULL;

	clear_bit(key, &mm->lru_gen.bitmap);

	return mmget_not_zero(mm) ? mm : NULL;
}

void lru_gen_add_mm(struct mm_struct *mm)
{
	int nid;
	struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
	struct lru_gen_mm_list *mm_list = get_mm_list(memcg);

	VM_WARN_ON_ONCE(!list_empty(&mm->lru_gen.list));
#ifdef CONFIG_MEMCG
	VM_WARN_ON_ONCE(mm->lru_gen.memcg);
	mm->lru_gen.memcg = memcg;
#endif
	spin_lock(&mm_list->lock);

	for_each_node_state(nid, N_MEMORY) {
		struct lruvec *lruvec = get_lruvec(memcg, nid);
		struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);

		/* the first addition since the last iteration */
		if (mm_state->tail == &mm_list->fifo)
			mm_state->tail = &mm->lru_gen.list;
	}

	list_add_tail(&mm->lru_gen.list, &mm_list->fifo);

	spin_unlock(&mm_list->lock);
}

void lru_gen_del_mm(struct mm_struct *mm)
{
	int nid;
	struct lru_gen_mm_list *mm_list;
	struct mem_cgroup *memcg = NULL;

	if (list_empty(&mm->lru_gen.list))
		return;

#ifdef CONFIG_MEMCG
	memcg = mm->lru_gen.memcg;
#endif
	mm_list = get_mm_list(memcg);

	spin_lock(&mm_list->lock);

	for_each_node(nid) {
		struct lruvec *lruvec = get_lruvec(memcg, nid);
		struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);

		/* where the current iteration continues after */
		if (mm_state->head == &mm->lru_gen.list)
			mm_state->head = mm_state->head->prev;

		/* where the last iteration ended before */
		if (mm_state->tail == &mm->lru_gen.list)
			mm_state->tail = mm_state->tail->next;
	}

	list_del_init(&mm->lru_gen.list);

	spin_unlock(&mm_list->lock);

#ifdef CONFIG_MEMCG
	mem_cgroup_put(mm->lru_gen.memcg);
	mm->lru_gen.memcg = NULL;
#endif
}

#ifdef CONFIG_MEMCG
void lru_gen_migrate_mm(struct mm_struct *mm)
{
	struct mem_cgroup *memcg;
	struct task_struct *task = rcu_dereference_protected(mm->owner, true);

	VM_WARN_ON_ONCE(task->mm != mm);
	lockdep_assert_held(&task->alloc_lock);

	/* for mm_update_next_owner() */
	if (mem_cgroup_disabled())
		return;

	/* migration can happen before addition */
	if (!mm->lru_gen.memcg)
		return;

	rcu_read_lock();
	memcg = mem_cgroup_from_task(task);
	rcu_read_unlock();
	if (memcg == mm->lru_gen.memcg)
		return;

	VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list));

	lru_gen_del_mm(mm);
	lru_gen_add_mm(mm);
}
#endif

#else /* !CONFIG_LRU_GEN_WALKS_MMU */

static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg)
{
	return NULL;
}

static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec)
{
	return NULL;
}

static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk)
{
	return NULL;
}

#endif

static void reset_mm_stats(struct lru_gen_mm_walk *walk, bool last)
{
	int i;
	int hist;
	struct lruvec *lruvec = walk->lruvec;
	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);

	lockdep_assert_held(&get_mm_list(lruvec_memcg(lruvec))->lock);

	hist = lru_hist_from_seq(walk->seq);

	for (i = 0; i < NR_MM_STATS; i++) {
		WRITE_ONCE(mm_state->stats[hist][i],
			   mm_state->stats[hist][i] + walk->mm_stats[i]);
		walk->mm_stats[i] = 0;
	}

	if (NR_HIST_GENS > 1 && last) {
		hist = lru_hist_from_seq(walk->seq + 1);

		for (i = 0; i < NR_MM_STATS; i++)
			WRITE_ONCE(mm_state->stats[hist][i], 0);
	}
}

static bool iterate_mm_list(struct lru_gen_mm_walk *walk, struct mm_struct **iter)
{
	bool first = false;
	bool last = false;
	struct mm_struct *mm = NULL;
	struct lruvec *lruvec = walk->lruvec;
	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
	struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);

	/*
	 * mm_state->seq is incremented after each iteration of mm_list. There
	 * are three interesting cases for this page table walker:
	 * 1. It tries to start a new iteration with a stale max_seq: there is
	 *    nothing left to do.
	 * 2. It started the next iteration: it needs to reset the Bloom filter
	 *    so that a fresh set of PTE tables can be recorded.
	 * 3. It ended the current iteration: it needs to reset the mm stats
	 *    counters and tell its caller to increment max_seq.
	 */
	spin_lock(&mm_list->lock);

	VM_WARN_ON_ONCE(mm_state->seq + 1 < walk->seq);

	if (walk->seq <= mm_state->seq)
		goto done;

	if (!mm_state->head)
		mm_state->head = &mm_list->fifo;

	if (mm_state->head == &mm_list->fifo)
		first = true;

	do {
		mm_state->head = mm_state->head->next;
		if (mm_state->head == &mm_list->fifo) {
			WRITE_ONCE(mm_state->seq, mm_state->seq + 1);
			last = true;
			break;
		}

		/* force scan for those added after the last iteration */
		if (!mm_state->tail || mm_state->tail == mm_state->head) {
			mm_state->tail = mm_state->head->next;
			walk->force_scan = true;
		}
	} while (!(mm = get_next_mm(walk)));
done:
	if (*iter || last)
		reset_mm_stats(walk, last);

	spin_unlock(&mm_list->lock);

	if (mm && first)
		reset_bloom_filter(mm_state, walk->seq + 1);

	if (*iter)
		mmput_async(*iter);

	*iter = mm;

	return last;
}

static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long seq)
{
	bool success = false;
	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
	struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);

	spin_lock(&mm_list->lock);

	VM_WARN_ON_ONCE(mm_state->seq + 1 < seq);

	if (seq > mm_state->seq) {
		mm_state->head = NULL;
		mm_state->tail = NULL;
		WRITE_ONCE(mm_state->seq, mm_state->seq + 1);
		success = true;
	}

	spin_unlock(&mm_list->lock);

	return success;
}

/******************************************************************************
 *                          PID controller
 ******************************************************************************/

/*
 * A feedback loop based on Proportional-Integral-Derivative (PID) controller.
 *
 * The P term is refaulted/(evicted+protected) from a tier in the generation
 * currently being evicted; the I term is the exponential moving average of the
 * P term over the generations previously evicted, using the smoothing factor
 * 1/2; the D term isn't supported.
 *
 * The setpoint (SP) is always the first tier of one type; the process variable
 * (PV) is either any tier of the other type or any other tier of the same
 * type.
 *
 * The error is the difference between the SP and the PV; the correction is to
 * turn off protection when SP>PV or turn on protection when SP<PV.
 *
 * For future optimizations:
 * 1. The D term may discount the other two terms over time so that long-lived
 *    generations can resist stale information.
 */
struct ctrl_pos {
	unsigned long refaulted;
	unsigned long total;
	int gain;
};

static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain,
			  struct ctrl_pos *pos)
{
	struct lru_gen_folio *lrugen = &lruvec->lrugen;
	int hist = lru_hist_from_seq(lrugen->min_seq[type]);

	pos->refaulted = lrugen->avg_refaulted[type][tier] +
			 atomic_long_read(&lrugen->refaulted[hist][type][tier]);
	pos->total = lrugen->avg_total[type][tier] +
		     atomic_long_read(&lrugen->evicted[hist][type][tier]);
	if (tier)
		pos->total += lrugen->protected[hist][type][tier - 1];
	pos->gain = gain;
}

static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover)
{
	int hist, tier;
	struct lru_gen_folio *lrugen = &lruvec->lrugen;
	bool clear = carryover ? NR_HIST_GENS == 1 : NR_HIST_GENS > 1;
	unsigned long seq = carryover ? lrugen->min_seq[type] : lrugen->max_seq + 1;

	lockdep_assert_held(&lruvec->lru_lock);

	if (!carryover && !clear)
		return;

	hist = lru_hist_from_seq(seq);

	for (tier = 0; tier < MAX_NR_TIERS; tier++) {
		if (carryover) {
			unsigned long sum;

			sum = lrugen->avg_refaulted[type][tier] +
			      atomic_long_read(&lrugen->refaulted[hist][type][tier]);
			WRITE_ONCE(lrugen->avg_refaulted[type][tier], sum / 2);

			sum = lrugen->avg_total[type][tier] +
			      atomic_long_read(&lrugen->evicted[hist][type][tier]);
			if (tier)
				sum += lrugen->protected[hist][type][tier - 1];
			WRITE_ONCE(lrugen->avg_total[type][tier], sum / 2);
		}

		if (clear) {
			atomic_long_set(&lrugen->refaulted[hist][type][tier], 0);
			atomic_long_set(&lrugen->evicted[hist][type][tier], 0);
			if (tier)
				WRITE_ONCE(lrugen->protected[hist][type][tier - 1], 0);
		}
	}
}

static bool positive_ctrl_err(struct ctrl_pos *sp, struct ctrl_pos *pv)
{
	/*
	 * Return true if the PV has a limited number of refaults or a lower
	 * refaulted/total than the SP.
	 */
	return pv->refaulted < MIN_LRU_BATCH ||
	       pv->refaulted * (sp->total + MIN_LRU_BATCH) * sp->gain <=
	       (sp->refaulted + 1) * pv->total * pv->gain;
}

/******************************************************************************
 *                          the aging
 ******************************************************************************/

/* promote pages accessed through page tables */
static int folio_update_gen(struct folio *folio, int gen)
{
	unsigned long new_flags, old_flags = READ_ONCE(folio->flags);

	VM_WARN_ON_ONCE(gen >= MAX_NR_GENS);
	VM_WARN_ON_ONCE(!rcu_read_lock_held());

	do {
		/* lru_gen_del_folio() has isolated this page? */
		if (!(old_flags & LRU_GEN_MASK)) {
			/* for shrink_folio_list() */
			new_flags = old_flags | BIT(PG_referenced);
			continue;
		}

		new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS);
		new_flags |= (gen + 1UL) << LRU_GEN_PGOFF;
	} while (!try_cmpxchg(&folio->flags, &old_flags, new_flags));

	return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
}

/* protect pages accessed multiple times through file descriptors */
static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
{
	int type = folio_is_file_lru(folio);
	struct lru_gen_folio *lrugen = &lruvec->lrugen;
	int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]);
	unsigned long new_flags, old_flags = READ_ONCE(folio->flags);

	VM_WARN_ON_ONCE_FOLIO(!(old_flags & LRU_GEN_MASK), folio);

	do {
		new_gen = ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
		/* folio_update_gen() has promoted this page? */
		if (new_gen >= 0 && new_gen != old_gen)
			return new_gen;

		new_gen = (old_gen + 1) % MAX_NR_GENS;

		new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS);
		new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF;
		/* for folio_end_writeback() */
		if (reclaiming)
			new_flags |= BIT(PG_reclaim);
	} while (!try_cmpxchg(&folio->flags, &old_flags, new_flags));

	lru_gen_update_size(lruvec, folio, old_gen, new_gen);

	return new_gen;
}

static void update_batch_size(struct lru_gen_mm_walk *walk, 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);

	VM_WARN_ON_ONCE(old_gen >= MAX_NR_GENS);
	VM_WARN_ON_ONCE(new_gen >= MAX_NR_GENS);

	walk->batched++;

	walk->nr_pages[old_gen][type][zone] -= delta;
	walk->nr_pages[new_gen][type][zone] += delta;
}

static void reset_batch_size(struct lru_gen_mm_walk *walk)
{
	int gen, type, zone;
	struct lruvec *lruvec = walk->lruvec;
	struct lru_gen_folio *lrugen = &lruvec->lrugen;

	walk->batched = 0;

	for_each_gen_type_zone(gen, type, zone) {
		enum lru_list lru = type * LRU_INACTIVE_FILE;
		int delta = walk->nr_pages[gen][type][zone];

		if (!delta)
			continue;

		walk->nr_pages[gen][type][zone] = 0;
		WRITE_ONCE(lrugen->nr_pages[gen][type][zone],
			   lrugen->nr_pages[gen][type][zone] + delta);

		if (lru_gen_is_active(lruvec, gen))
			lru += LRU_ACTIVE;
		__update_lru_size(lruvec, lru, zone, delta);
	}
}

static int should_skip_vma(unsigned long start, unsigned long end, struct mm_walk *args)
{
	struct address_space *mapping;
	struct vm_area_struct *vma = args->vma;
	struct lru_gen_mm_walk *walk = args->private;

	if (!vma_is_accessible(vma))
		return true;

	if (is_vm_hugetlb_page(vma))
		return true;

	if (!vma_has_recency(vma))
		return true;

	if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL))
		return true;

	if (vma == get_gate_vma(vma->vm_mm))
		return true;

	if (vma_is_anonymous(vma))
		return !walk->can_swap;

	if (WARN_ON_ONCE(!vma->vm_file || !vma->vm_file->f_mapping))
		return true;

	mapping = vma->vm_file->f_mapping;
	if (mapping_unevictable(mapping))
		return true;

	if (shmem_mapping(mapping))
		return !walk->can_swap;

	/* to exclude special mappings like dax, etc. */
	return !mapping->a_ops->read_folio;
}

/*
 * Some userspace memory allocators map many single-page VMAs. Instead of
 * returning back to the PGD table for each of such VMAs, finish an entire PMD
 * table to reduce zigzags and improve cache performance.
 */
static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk *args,
			 unsigned long *vm_start, unsigned long *vm_end)
{
	unsigned long start = round_up(*vm_end, size);
	unsigned long end = (start | ~mask) + 1;
	VMA_ITERATOR(vmi, args->mm, start);

	VM_WARN_ON_ONCE(mask & size);
	VM_WARN_ON_ONCE((start & mask) != (*vm_start & mask));

	for_each_vma(vmi, args->vma) {
		if (end && end <= args->vma->vm_start)
			return false;

		if (should_skip_vma(args->vma->vm_start, args->vma->vm_end, args))
			continue;

		*vm_start = max(start, args->vma->vm_start);
		*vm_end = min(end - 1, args->vma->vm_end - 1) + 1;

		return true;
	}

	return false;
}