OpenCloudOS-Kernel/mm/workingset.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Workingset detection
 *
 * Copyright (C) 2013 Red Hat, Inc., Johannes Weiner
 */

#include <linux/memcontrol.h>
#include <linux/mm_inline.h>
#include <linux/writeback.h>
#include <linux/shmem_fs.h>
#include <linux/pagemap.h>
#include <linux/atomic.h>
#include <linux/module.h>
#include <linux/swap.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/mm.h>

/*
 *		Double CLOCK lists
 *
 * Per node, two clock lists are maintained for file pages: the
 * inactive and the active list.  Freshly faulted pages start out at
 * the head of the inactive list and page reclaim scans pages from the
 * tail.  Pages that are accessed multiple times on the inactive list
 * are promoted to the active list, to protect them from reclaim,
 * whereas active pages are demoted to the inactive list when the
 * active list grows too big.
 *
 *   fault ------------------------+
 *                                 |
 *              +--------------+   |            +-------------+
 *   reclaim <- |   inactive   | <-+-- demotion |    active   | <--+
 *              +--------------+                +-------------+    |
 *                     |                                           |
 *                     +-------------- promotion ------------------+
 *
 *
 *		Access frequency and refault distance
 *
 * A workload is thrashing when its pages are frequently used but they
 * are evicted from the inactive list every time before another access
 * would have promoted them to the active list.
 *
 * In cases where the average access distance between thrashing pages
 * is bigger than the size of memory there is nothing that can be
 * done - the thrashing set could never fit into memory under any
 * circumstance.
 *
 * However, the average access distance could be bigger than the
 * inactive list, yet smaller than the size of memory.  In this case,
 * the set could fit into memory if it weren't for the currently
 * active pages - which may be used more, hopefully less frequently:
 *
 *      +-memory available to cache-+
 *      |                           |
 *      +-inactive------+-active----+
 *  a b | c d e f g h i | J K L M N |
 *      +---------------+-----------+
 *
 * It is prohibitively expensive to accurately track access frequency
 * of pages.  But a reasonable approximation can be made to measure
 * thrashing on the inactive list, after which refaulting pages can be
 * activated optimistically to compete with the existing active pages.
 *
 * Approximating inactive page access frequency - Observations:
 *
 * 1. When a page is accessed for the first time, it is added to the
 *    head of the inactive list, slides every existing inactive page
 *    towards the tail by one slot, and pushes the current tail page
 *    out of memory.
 *
 * 2. When a page is accessed for the second time, it is promoted to
 *    the active list, shrinking the inactive list by one slot.  This
 *    also slides all inactive pages that were faulted into the cache
 *    more recently than the activated page towards the tail of the
 *    inactive list.
 *
 * Thus:
 *
 * 1. The sum of evictions and activations between any two points in
 *    time indicate the minimum number of inactive pages accessed in
 *    between.
 *
 * 2. Moving one inactive page N page slots towards the tail of the
 *    list requires at least N inactive page accesses.
 *
 * Combining these:
 *
 * 1. When a page is finally evicted from memory, the number of
 *    inactive pages accessed while the page was in cache is at least
 *    the number of page slots on the inactive list.
 *
 * 2. In addition, measuring the sum of evictions and activations (E)
 *    at the time of a page's eviction, and comparing it to another
 *    reading (R) at the time the page faults back into memory tells
 *    the minimum number of accesses while the page was not cached.
 *    This is called the refault distance.
 *
 * Because the first access of the page was the fault and the second
 * access the refault, we combine the in-cache distance with the
 * out-of-cache distance to get the complete minimum access distance
 * of this page:
 *
 *      NR_inactive + (R - E)
 *
 * And knowing the minimum access distance of a page, we can easily
 * tell if the page would be able to stay in cache assuming all page
 * slots in the cache were available:
 *
 *   NR_inactive + (R - E) <= NR_inactive + NR_active
 *
 * which can be further simplified to
 *
 *   (R - E) <= NR_active
 *
 * Put into words, the refault distance (out-of-cache) can be seen as
 * a deficit in inactive list space (in-cache).  If the inactive list
 * had (R - E) more page slots, the page would not have been evicted
 * in between accesses, but activated instead.  And on a full system,
 * the only thing eating into inactive list space is active pages.
 *
 *
 *		Refaulting inactive pages
 *
 * All that is known about the active list is that the pages have been
 * accessed more than once in the past.  This means that at any given
 * time there is actually a good chance that pages on the active list
 * are no longer in active use.
 *
 * So when a refault distance of (R - E) is observed and there are at
 * least (R - E) active pages, the refaulting page is activated
 * optimistically in the hope that (R - E) active pages are actually
 * used less frequently than the refaulting page - or even not used at
 * all anymore.
 *
 * That means if inactive cache is refaulting with a suitable refault
 * distance, we assume the cache workingset is transitioning and put
 * pressure on the current active list.
 *
 * If this is wrong and demotion kicks in, the pages which are truly
 * used more frequently will be reactivated while the less frequently
 * used once will be evicted from memory.
 *
 * But if this is right, the stale pages will be pushed out of memory
 * and the used pages get to stay in cache.
 *
 *		Refaulting active pages
 *
 * If on the other hand the refaulting pages have recently been
 * deactivated, it means that the active list is no longer protecting
 * actively used cache from reclaim. The cache is NOT transitioning to
 * a different workingset; the existing workingset is thrashing in the
 * space allocated to the page cache.
 *
 *
 *		Implementation
 *
 * For each node's LRU lists, a counter for inactive evictions and
 * activations is maintained (node->nonresident_age).
 *
 * On eviction, a snapshot of this counter (along with some bits to
 * identify the node) is stored in the now empty page cache
 * slot of the evicted page.  This is called a shadow entry.
 *
 * On cache misses for which there are shadow entries, an eligible
 * refault distance will immediately activate the refaulting page.
 */

#define WORKINGSET_SHIFT 1
#define EVICTION_SHIFT	((BITS_PER_LONG - BITS_PER_XA_VALUE) +	\
			 WORKINGSET_SHIFT + NODES_SHIFT + \
			 MEM_CGROUP_ID_SHIFT)
#define EVICTION_MASK	(~0UL >> EVICTION_SHIFT)

/*
 * Eviction timestamps need to be able to cover the full range of
 * actionable refaults. However, bits are tight in the xarray
 * entry, and after storing the identifier for the lruvec there might
 * not be enough left to represent every single actionable refault. In
 * that case, we have to sacrifice granularity for distance, and group
 * evictions into coarser buckets by shaving off lower timestamp bits.
 */
static unsigned int bucket_order __read_mostly;

/*
 * MGLRU may reuse some bits of eviction for better accuracy, but
 * LRU_GEN_WIDTH and LRU_REFS_WIDTH already took some place.
 */
#define LRU_GEN_EVICTION_SHIFT		(EVICTION_SHIFT + LRU_GEN_WIDTH + LRU_REFS_WIDTH)
#define LRU_GEN_EVICTION_MASK		(EVICTION_MASK >> (LRU_GEN_WIDTH + LRU_REFS_WIDTH))
#define LRU_GEN_EVICTION_GEN_MASK	(LRU_GEN_EVICTION_MASK & ~(LRU_GEN_EVICTION_MASK << (LRU_GEN_WIDTH + LRU_REFS_WIDTH)))
static unsigned int lru_gen_bucket_order __read_mostly;

static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction,
			 bool workingset)
{
	eviction &= EVICTION_MASK;
	eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
	eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
	eviction = (eviction << WORKINGSET_SHIFT) | workingset;

	return xa_mk_value(eviction);
}

static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
			  unsigned long *evictionp, bool *workingsetp)
{
	unsigned long entry = xa_to_value(shadow);
	int memcgid, nid;
	bool workingset;

	workingset = entry & ((1UL << WORKINGSET_SHIFT) - 1);
	entry >>= WORKINGSET_SHIFT;
	nid = entry & ((1UL << NODES_SHIFT) - 1);
	entry >>= NODES_SHIFT;
	memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1);
	entry >>= MEM_CGROUP_ID_SHIFT;

	*memcgidp = memcgid;
	*pgdat = NODE_DATA(nid);
	*evictionp = entry;
	*workingsetp = workingset;
}

#ifdef CONFIG_WORKINGSET_EVICT_EVAL
void workingset_evict_file(struct lruvec *lruvec, unsigned long nr_pages)
{
	do {
		atomic_long_add(nr_pages, &lruvec->evicted_file);
	} while ((lruvec = parent_lruvec(lruvec)));
}
#endif

#ifdef CONFIG_LRU_GEN

static void *lru_gen_eviction(struct page *page)
{
	int hist;
	unsigned long token;
	unsigned long min_seq;
	struct lruvec *lruvec;
	struct lru_gen_struct *lrugen;
	int type = page_is_file_lru(page);
	int delta = hpage_nr_pages(page);
	int refs = page_lru_refs(page);
	int tier = lru_tier_from_refs(refs);
	struct mem_cgroup *memcg = page_memcg(page);
	struct pglist_data *pgdat = page_pgdat(page);

	/* XXX: kasong: during testing period, keep this BUG_ON to catch
	 * potential tailing page bug due to folio modification, or maybe
	 * just move this to hpage helpers */
	VM_BUG_ON_PAGE(PageTail(page), page);
	BUILD_BUG_ON(LRU_GEN_WIDTH + LRU_REFS_WIDTH > BITS_PER_LONG - EVICTION_SHIFT);

	lruvec = mem_cgroup_lruvec(memcg, pgdat);
	lrugen = &lruvec->lrugen;
	min_seq = READ_ONCE(lrugen->min_seq[type]);

	token = atomic_long_read(&lruvec->nonresident_age);
	token >>= lru_gen_bucket_order;
	token &= LRU_GEN_EVICTION_MASK;
	token <<= (LRU_GEN_WIDTH + LRU_REFS_WIDTH);
	token |= (((min_seq << LRU_REFS_WIDTH) | max(refs - 1, 0)) & LRU_GEN_EVICTION_GEN_MASK);

	hist = lru_hist_from_seq(min_seq);
	atomic_long_add(delta, &lrugen->evicted[hist][type][tier]);

	/* keep the workingset ticking */
	workingset_age_nonresident(lruvec, delta);
#ifdef CONFIG_WORKINGSET_EVICT_EVAL
	workingset_evict_file(lruvec, delta);
#endif

	return pack_shadow(mem_cgroup_id(memcg), pgdat, token, refs);
}

static void lru_gen_refault(struct page *page, void *shadow, unsigned long *eviction)
{
	int hist, tier, refs;
	int memcg_id;
	bool workingset;
	unsigned long token;
	unsigned long min_seq;
	struct lruvec *lruvec;
	struct lru_gen_struct *lrugen;
	struct mem_cgroup *memcg;
	struct pglist_data *pgdat;
	int type = page_is_file_lru(page);
	int delta = hpage_nr_pages(page);

	/* XXX: kasong: during testing period, keep this BUG_ON to catch
	 * potential tailing page bug due to folio modification, or maybe
	 * just move this to hpage helpers */
	VM_BUG_ON_PAGE(PageTail(page), page);

	unpack_shadow(shadow, &memcg_id, &pgdat, &token, &workingset);
	*eviction = token >> (LRU_GEN_WIDTH + LRU_REFS_WIDTH);
	*eviction <<= lru_gen_bucket_order;
	token &= LRU_GEN_EVICTION_GEN_MASK;

	if (pgdat != page_pgdat(page))
		return;

	rcu_read_lock();

	memcg = page_memcg_rcu(page);
	if (memcg_id != mem_cgroup_id(memcg))
		goto unlock;

	lruvec = mem_cgroup_lruvec(memcg, pgdat);
	lrugen = &lruvec->lrugen;

	min_seq = READ_ONCE(lrugen->min_seq[type]);
	if ((token >> LRU_REFS_WIDTH) != (min_seq & (BIT(LRU_GEN_WIDTH) - 1)))
		goto unlock;

	hist = lru_hist_from_seq(min_seq);
	/* see the comment in page_lru_refs() */
	refs = (token & (BIT(LRU_REFS_WIDTH) - 1)) + workingset;
	tier = lru_tier_from_refs(refs);

	atomic_long_add(delta, &lrugen->refaulted[hist][type][tier]);
	mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + type, delta);

	/*
	 * Count the following two cases as stalls:
	 * 1. For pages accessed through page tables, hotter pages pushed out
	 *    hot pages which refaulted immediately.
	 * 2. For pages accessed multiple times through file descriptors,
	 *    numbers of accesses might have been out of the range.
	 */
	if (lru_gen_in_fault() || refs == BIT(LRU_REFS_WIDTH)) {
		SetPageWorkingset(page);
		mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta);
	}
unlock:
	rcu_read_unlock();
}

#else /* !CONFIG_LRU_GEN */

static void *lru_gen_eviction(struct page *page)
{
	return NULL;
}

static void lru_gen_refault(struct page *page, void *shadow, unsigned long *eviction)
{
	return;
}

#endif /* CONFIG_LRU_GEN */

/* Evaluate the effectively evicted file workingset size */
#ifdef CONFIG_WORKINGSET_EVICT_EVAL

/* Global aggregator work */
static struct delayed_work avgs_work;

/*
 * If a page is evicted and never come back, either this page is really cold or it
 * is deleted on disk.
 *
 * For cold page, it could take up all of memory until kswapd start to shrink it.
 * For deleted page, the shadow will be gone too, so no refault.
 *
 * If a page comes back before it's shadow is released, that's a refault, which means
 * file page reclaim have gone over-aggressive and that page would not have been evicted
 * if all the page, include it self, stayed in memory.
 */
static void workingset_refault_evaluation(struct page *page, struct mem_cgroup *memcg,
					  struct pglist_data *pgdat, unsigned long eviction)
{
	bool file = page_is_file_lru(page);
	unsigned long refault, refault_distance;
	unsigned long memcg_limit_pg, memcg_usage_pg;
	unsigned long balanced_value;
	unsigned long remain_distance;

	struct lruvec *lruvec;

	/*
	 * We only track file page, anon page can be simply obtained by reading
	 * swap device status.
	 */
	if (!file)
		return;

	/* If original memcg is gone, account this to new memcg the page being read from */
	if (!memcg) {
		memcg = page_memcg(page);
		pgdat = page_pgdat(page);
	}

	lruvec = mem_cgroup_lruvec(memcg, pgdat);
	/* XXX: memcg can be NULL, go through lruvec */
	if (!memcg)
		memcg = lruvec_memcg(lruvec);

	if (!memcg)
		return;

	/*
	 * Calc the refault distance and limit by available memory.
	 */
	refault = atomic_long_read(&lruvec->nonresident_age);
	if (lru_gen_enabled())
		refault_distance = (refault - eviction) & LRU_GEN_EVICTION_MASK;
	else
		refault_distance = (refault - eviction) & EVICTION_MASK;

	/* If limit not set, use total ram size */
	memcg_limit_pg = memcg->memory.max;
	if (memcg_limit_pg == PAGE_COUNTER_MAX)
		memcg_limit_pg = totalram_pages();

	/* Get the current memory usage of this cgroup */
	if (mem_cgroup_is_root(memcg))
		memcg_usage_pg = memcg_page_state(memcg, NR_FILE_PAGES) + memcg_page_state(memcg, NR_ANON_MAPPED);
	else
		memcg_usage_pg = page_counter_read(&memcg->memory);

	remain_distance = memcg_limit_pg - memcg_usage_pg;
	balanced_value = min(refault_distance, remain_distance);

	do {
		/*
		 * Not taking any lock, for better performance, may lead to some
		 * event got lost, but it's just a estimation anyway.
		 */
		WRITE_ONCE(lruvec->eval_count, lruvec->eval_count + 1);
		WRITE_ONCE(lruvec->total_distance, lruvec->total_distance + balanced_value);
	} while ((lruvec = parent_lruvec(lruvec)));
}

#define FSHIFT		12		/* 12 of bits of precision */
#define FIXED_P		(1 << FSHIFT)	/* fixed-point */
#define EVAL_FREQ	(10 * HZ + 1 )	/* 10 sec intervals */
#define EXP_1		3467		/* 1/exp(10sec/1min), caculated with FIXED_P / math.exp(10.0/60) */
#define EXP_10		4028		/* 1/exp(10sec/10min), same as above */
#define EXP_30		4073		/* 1/exp(10sec/30min), same as above */
#define EXP_60		4084		/* 1/exp(10sec/60min), same as above */

/*
 * a1 = a0 * e + a * (1 - e), same as calc_load.
 */
static inline unsigned long
calc_avg(unsigned long prev_val, unsigned long exp, unsigned long next_val)
{
	unsigned long ret;

	ret = prev_val * exp + next_val * (FIXED_P - exp);
	if (next_val >= prev_val)
		ret += FIXED_P-1;

	return ret / FIXED_P;
}

/*
 * Trigger every 10s (EVAL_FREQ).
 */
static void evict_eval_work(struct work_struct *work)
{
	struct delayed_work *dwork;
	struct mem_cgroup *memcg;
	unsigned long memcg_limit_pg, memcg_usage_pg, memcg_avail_pg;

	/*
	 * Three things to calculate here:
	 *
	 * memcg->workingset_valid_eviction_*:  corrected reading of valid evictions
	 * (may plus activitions) of a memcg. Indicats the valid amount of memory ever get evicted.
	 * This value tends to get really large, so correct it in a way to limit it's size.
	 *
	 * lruvec->workingset_watermark_*: corrected max value of avg refault distance
	 * of a memcg.
	 *
	 * lruvec->workingset_refault_distance_*: avg refault distance
	 * of a memcg. Indicats the most recent refault distances.
	 *
	 */
	memcg = mem_cgroup_iter(NULL, NULL, NULL);
	for (; memcg != NULL; memcg = mem_cgroup_iter(NULL, memcg, NULL)) {
		int nid;
		unsigned long lru_period_distance, lru_period_watermark;
		unsigned long cg_eviction = 0;
		unsigned long active_page = 0;
		unsigned long remaining_watermark;

		/* If limit not set, use total ram size */
		memcg_limit_pg = memcg->memory.max;
		if (memcg_limit_pg == PAGE_COUNTER_MAX)
			memcg_limit_pg = totalram_pages();

		/* Get the current memory usage of this cgroup */
		if (mem_cgroup_is_root(memcg))
			memcg_usage_pg = memcg_page_state(memcg, NR_FILE_PAGES) + memcg_page_state(memcg, NR_ANON_MAPPED);
		else
			memcg_usage_pg = page_counter_read(&memcg->memory);

		/* Get the current available memory of this cgroup, neither valid_eviction or refault should exceed this */
		memcg_avail_pg = memcg_limit_pg - memcg_usage_pg;

		/* Calculate workingset_refault_distance_* */
		remaining_watermark = memcg_avail_pg;
		for_each_node_state(nid, N_MEMORY) {
			struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec;

			/* If refault ever happend, update using new value, else keep momentum using last value */
			if (lruvec->eval_count) {
				lru_period_distance = READ_ONCE(lruvec->total_distance) / READ_ONCE(lruvec->eval_count);

				WRITE_ONCE(lruvec->eval_count, 0);
				WRITE_ONCE(lruvec->total_distance, 0);
			} else {
				lru_period_distance = 0;
			}

			if (lru_period_distance) {
				lruvec->workingset_refault_distance_last = lru_period_distance;
				lruvec->workingset_refault_distance_avg[0] = calc_avg(
						lruvec->workingset_refault_distance_avg[0], EXP_1, lru_period_distance);
				lruvec->workingset_refault_distance_avg[1] = calc_avg(
						lruvec->workingset_refault_distance_avg[1], EXP_10, lru_period_distance);
				lruvec->workingset_refault_distance_avg[2] = calc_avg(
						lruvec->workingset_refault_distance_avg[2], EXP_30, lru_period_distance);
			}

			/* Make sure the watermark drops slowly, and consider caches are drained to 0 after 1 more hour of idle */
			lru_period_watermark = max(lru_period_distance, lruvec->workingset_watermark_last);
			lru_period_watermark = calc_avg(lru_period_watermark, EXP_60, 0);

			/* Make sure all lruvec's refault distance doesn't add up to a value larger than total memory */
			lru_period_watermark = min(remaining_watermark, lru_period_watermark);

			lruvec->workingset_watermark_last = lru_period_watermark;
			lruvec->workingset_watermark_avg[0] = calc_avg(
					lruvec->workingset_watermark_avg[0], EXP_1, lru_period_watermark);
			lruvec->workingset_watermark_avg[1] = calc_avg(
					lruvec->workingset_watermark_avg[1], EXP_10, lru_period_watermark);
			lruvec->workingset_watermark_avg[2] = calc_avg(
					lruvec->workingset_watermark_avg[2], EXP_30, lru_period_watermark);
			remaining_watermark -= lru_period_watermark;

			/* For memcg's workingset_valid_eviction_* */
			active_page += lruvec_page_state(lruvec, NR_ACTIVE_FILE) + lruvec_page_state(lruvec, NR_ACTIVE_ANON);
			cg_eviction += atomic_long_read(&lruvec->evicted_file);
		}

		/* It could soon exceed memcg_avail_pg, balance using max memory and watermark */
		cg_eviction = min(cg_eviction, memcg_avail_pg);

		/*
		 * XXX: watermark is legacy only
		 */
		if (READ_ONCE(memcg->memory.watermark) > active_page)
			cg_eviction = min(cg_eviction, READ_ONCE(memcg->memory.watermark) - active_page);

		/* Make it a evict distance of about past hour */
		memcg->workingset_valid_eviction_last = max(cg_eviction, memcg->workingset_eviction_last) - memcg->workingset_eviction_last;
		memcg->workingset_eviction_last = calc_avg(memcg->workingset_eviction_last, EXP_60, cg_eviction);

		memcg->workingset_valid_eviction_avg[0] = calc_avg(
				memcg->workingset_valid_eviction_avg[0], EXP_1, memcg->workingset_valid_eviction_last);
		memcg->workingset_valid_eviction_avg[1] = calc_avg(
				memcg->workingset_valid_eviction_avg[1], EXP_10, memcg->workingset_valid_eviction_last);
		memcg->workingset_valid_eviction_avg[2] = calc_avg(
				memcg->workingset_valid_eviction_avg[2], EXP_30, memcg->workingset_valid_eviction_last);
	}

	dwork = to_delayed_work(work);
	schedule_delayed_work(dwork, EVAL_FREQ + 1);
}

static int __init workingset_file_eval_init(void)
{
	INIT_DELAYED_WORK(&avgs_work, evict_eval_work);
	schedule_delayed_work(&avgs_work, EVAL_FREQ + 1);

	return 0;
}
module_init(workingset_file_eval_init);
#else
static void workingset_refault_evaluation(struct page *page, struct mem_cgroup *memcg,
					  struct pglist_data *pgdat, unsigned long eviction)
{
	return;
}
#endif /* CONFIG_WORKINGSET_EVICT_EVAL */

/**
 * workingset_age_nonresident - age non-resident entries as LRU ages
 * @memcg: the lruvec that was aged
 * @nr_pages: the number of pages to count
 *
 * As in-memory pages are aged, non-resident pages need to be aged as
 * well, in order for the refault distances later on to be comparable
 * to the in-memory dimensions. This function allows reclaim and LRU
 * operations to drive the non-resident aging along in parallel.
 */
void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages)
{
	/*
	 * Reclaiming a cgroup means reclaiming all its children in a
	 * round-robin fashion. That means that each cgroup has an LRU
	 * order that is composed of the LRU orders of its child
	 * cgroups; and every page has an LRU position not just in the
	 * cgroup that owns it, but in all of that group's ancestors.
	 *
	 * So when the physical inactive list of a leaf cgroup ages,
	 * the virtual inactive lists of all its parents, including
	 * the root cgroup's, age as well.
	 */
	do {
		atomic_long_add(nr_pages, &lruvec->nonresident_age);
	} while ((lruvec = parent_lruvec(lruvec)));
}

/**
 * workingset_eviction - note the eviction of a page from memory
 * @target_memcg: the cgroup that is causing the reclaim
 * @page: the page being evicted
 *
 * Returns a shadow entry to be stored in @page->mapping->i_pages in place
 * of the evicted @page so that a later refault can be detected.
 */
void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
{
	struct pglist_data *pgdat = page_pgdat(page);
	unsigned long eviction;
	struct lruvec *lruvec;
	int memcgid;

	/* Page is fully exclusive and pins page->mem_cgroup */
	VM_BUG_ON_PAGE(PageLRU(page), page);
	VM_BUG_ON_PAGE(page_count(page), page);
	VM_BUG_ON_PAGE(!PageLocked(page), page);

	if (lru_gen_enabled())
		return lru_gen_eviction(page);

	lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
	/* XXX: target_memcg can be NULL, go through lruvec */
	memcgid = mem_cgroup_id(lruvec_memcg(lruvec));
	eviction = atomic_long_read(&lruvec->nonresident_age);
	eviction >>= bucket_order;
	workingset_age_nonresident(lruvec, thp_nr_pages(page));
#ifdef CONFIG_WORKINGSET_EVICT_EVAL
	workingset_evict_file(lruvec, thp_nr_pages(page));
#endif

	return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page));
}

/**
 * workingset_refault - evaluate the refault of a previously evicted page
 * @page: the freshly allocated replacement page
 * @shadow: shadow entry of the evicted page
 *
 * Calculates and evaluates the refault distance of the previously
 * evicted page in the context of the node and the memcg whose memory
 * pressure caused the eviction.
 */
void workingset_refault(struct page *page, void *shadow)
{
	bool file = page_is_file_lru(page);
	struct mem_cgroup *eviction_memcg;
	struct lruvec *eviction_lruvec;
	unsigned long refault_distance;
	unsigned long workingset_size;
	struct pglist_data *pgdat;
	struct mem_cgroup *memcg;
	unsigned long eviction;
	struct lruvec *lruvec;
	unsigned long refault;
	bool workingset;
	int memcgid;

	unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset);
	eviction <<= bucket_order;

	if (lru_gen_enabled()) {
		lru_gen_refault(page, shadow, &eviction);
		/* Simple diabled the workingset detection below, it's done by MGLRU already */
		workingset = false;
	}

	rcu_read_lock();
	/*
	 * Look up the memcg associated with the stored ID. It might
	 * have been deleted since the page's eviction.
	 *
	 * Note that in rare events the ID could have been recycled
	 * for a new cgroup that refaults a shared page. This is
	 * impossible to tell from the available data. However, this
	 * should be a rare and limited disturbance, and activations
	 * are always speculative anyway. Ultimately, it's the aging
	 * algorithm's job to shake out the minimum access frequency
	 * for the active cache.
	 *
	 * XXX: On !CONFIG_MEMCG, this will always return NULL; it
	 * would be better if the root_mem_cgroup existed in all
	 * configurations instead.
	 */
	eviction_memcg = mem_cgroup_from_id(memcgid);
	if (!mem_cgroup_disabled() && !eviction_memcg)
		goto out;
	eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat);
	refault = atomic_long_read(&eviction_lruvec->nonresident_age);

	/* For CONFIG_WORKINGSET_EVICT_EVAL */
	workingset_refault_evaluation(page, eviction_memcg, pgdat, eviction);

	/*
	 * Calculate the refault distance
	 *
	 * The unsigned subtraction here gives an accurate distance
	 * across nonresident_age overflows in most cases. There is a
	 * special case: usually, shadow entries have a short lifetime
	 * and are either refaulted or reclaimed along with the inode
	 * before they get too old.  But it is not impossible for the
	 * nonresident_age to lap a shadow entry in the field, which
	 * can then result in a false small refault distance, leading
	 * to a false activation should this old entry actually
	 * refault again.  However, earlier kernels used to deactivate
	 * unconditionally with *every* reclaim invocation for the
	 * longest time, so the occasional inappropriate activation
	 * leading to pressure on the active list is not a problem.
	 */
	if (lru_gen_enabled())
		refault_distance = (refault - eviction) & LRU_GEN_EVICTION_MASK;
	else
		refault_distance = (refault - eviction) & EVICTION_MASK;

	/*
	 * The activation decision for this page is made at the level
	 * where the eviction occurred, as that is where the LRU order
	 * during page reclaim is being determined.
	 *
	 * However, the cgroup that will own the page is the one that
	 * is actually experiencing the refault event.
	 */
	memcg = page_memcg(page);
	lruvec = mem_cgroup_lruvec(memcg, pgdat);

	inc_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file);

	/*
	 * Compare the distance to the existing workingset size. We
	 * don't activate pages that couldn't stay resident even if
	 * all the memory was available to the workingset. Whether
	 * workingset competition needs to consider anon or not depends
	 * on having swap.
	 */
	workingset_size = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE);
	if (!file) {
		workingset_size += lruvec_page_state(eviction_lruvec,
						     NR_INACTIVE_FILE);
	}
	if (mem_cgroup_get_nr_swap_pages(memcg) > 0) {
		workingset_size += lruvec_page_state(eviction_lruvec,
						     NR_ACTIVE_ANON);
		if (file) {
			workingset_size += lruvec_page_state(eviction_lruvec,
						     NR_INACTIVE_ANON);
		}
	}
	if (refault_distance > workingset_size)
		goto out;

	SetPageActive(page);
	workingset_age_nonresident(lruvec, thp_nr_pages(page));
	inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file);

	/* Page was active prior to eviction */
	if (workingset) {
		SetPageWorkingset(page);
		/* XXX: Move to lru_cache_add() when it supports new vs putback */
		lru_note_cost_page(page);
		inc_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file);
	}
out:
	rcu_read_unlock();
}

/**
 * workingset_activation - note a page activation
 * @page: page that is being activated
 */
void workingset_activation(struct page *page)
{
	struct mem_cgroup *memcg;
	struct lruvec *lruvec;

	rcu_read_lock();
	/*
	 * Filter non-memcg pages here, e.g. unmap can call
	 * mark_page_accessed() on VDSO pages.
	 *
	 * XXX: See workingset_refault() - this should return
	 * root_mem_cgroup even for !CONFIG_MEMCG.
	 */
	memcg = page_memcg_rcu(page);
	if (!mem_cgroup_disabled() && !memcg)
		goto out;
	lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
	workingset_age_nonresident(lruvec, thp_nr_pages(page));
out:
	rcu_read_unlock();
}

/*
 * Shadow entries reflect the share of the working set that does not
 * fit into memory, so their number depends on the access pattern of
 * the workload.  In most cases, they will refault or get reclaimed
 * along with the inode, but a (malicious) workload that streams
 * through files with a total size several times that of available
 * memory, while preventing the inodes from being reclaimed, can
 * create excessive amounts of shadow nodes.  To keep a lid on this,
 * track shadow nodes and reclaim them when they grow way past the
 * point where they would still be useful.
 */

static struct list_lru shadow_nodes;

void workingset_update_node(struct xa_node *node)
{
	/*
	 * Track non-empty nodes that contain only shadow entries;
	 * unlink those that contain pages or are being freed.
	 *
	 * Avoid acquiring the list_lru lock when the nodes are
	 * already where they should be. The list_empty() test is safe
	 * as node->private_list is protected by the i_pages lock.
	 */
	VM_WARN_ON_ONCE(!irqs_disabled());  /* For __inc_lruvec_page_state */

	if (node->count && node->count == node->nr_values) {
		if (list_empty(&node->private_list)) {
			list_lru_add(&shadow_nodes, &node->private_list);
			__inc_lruvec_slab_state(node, WORKINGSET_NODES);
		}
	} else {
		if (!list_empty(&node->private_list)) {
			list_lru_del(&shadow_nodes, &node->private_list);
			__dec_lruvec_slab_state(node, WORKINGSET_NODES);
		}
	}
}

static unsigned long count_shadow_nodes(struct shrinker *shrinker,
					struct shrink_control *sc)
{
	unsigned long max_nodes;
	unsigned long nodes;
	unsigned long pages;

	nodes = list_lru_shrink_count(&shadow_nodes, sc);

	/*
	 * Approximate a reasonable limit for the nodes
	 * containing shadow entries. We don't need to keep more
	 * shadow entries than possible pages on the active list,
	 * since refault distances bigger than that are dismissed.
	 *
	 * The size of the active list converges toward 100% of
	 * overall page cache as memory grows, with only a tiny
	 * inactive list. Assume the total cache size for that.
	 *
	 * Nodes might be sparsely populated, with only one shadow
	 * entry in the extreme case. Obviously, we cannot keep one
	 * node for every eligible shadow entry, so compromise on a
	 * worst-case density of 1/8th. Below that, not all eligible
	 * refaults can be detected anymore.
	 *
	 * On 64-bit with 7 xa_nodes per page and 64 slots
	 * each, this will reclaim shadow entries when they consume
	 * ~1.8% of available memory:
	 *
	 * PAGE_SIZE / xa_nodes / node_entries * 8 / PAGE_SIZE
	 */
#ifdef CONFIG_MEMCG
	if (sc->memcg) {
		struct lruvec *lruvec;
		int i;

		lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
		for (pages = 0, i = 0; i < NR_LRU_LISTS; i++)
			pages += lruvec_page_state_local(lruvec,
							 NR_LRU_BASE + i);
		pages += lruvec_page_state_local(
			lruvec, NR_SLAB_RECLAIMABLE_B) >> PAGE_SHIFT;
		pages += lruvec_page_state_local(
			lruvec, NR_SLAB_UNRECLAIMABLE_B) >> PAGE_SHIFT;
	} else
#endif
		pages = node_present_pages(sc->nid);

	max_nodes = pages >> (XA_CHUNK_SHIFT - 3);

	if (!nodes)
		return SHRINK_EMPTY;

	if (nodes <= max_nodes)
		return 0;
	return nodes - max_nodes;
}

static enum lru_status shadow_lru_isolate(struct list_head *item,
					  struct list_lru_one *lru,
					  spinlock_t *lru_lock,
					  void *arg) __must_hold(lru_lock)
{
	struct xa_node *node = container_of(item, struct xa_node, private_list);
	XA_STATE(xas, node->array, 0);
	struct address_space *mapping;
	int ret;

	/*
	 * Page cache insertions and deletions synchroneously maintain
	 * the shadow node LRU under the i_pages lock and the
	 * lru_lock.  Because the page cache tree is emptied before
	 * the inode can be destroyed, holding the lru_lock pins any
	 * address_space that has nodes on the LRU.
	 *
	 * We can then safely transition to the i_pages lock to
	 * pin only the address_space of the particular node we want
	 * to reclaim, take the node off-LRU, and drop the lru_lock.
	 */

	mapping = container_of(node->array, struct address_space, i_pages);

	/* Coming from the list, invert the lock order */
	if (!xa_trylock(&mapping->i_pages)) {
		spin_unlock_irq(lru_lock);
		ret = LRU_RETRY;
		goto out;
	}

	list_lru_isolate(lru, item);
	__dec_lruvec_slab_state(node, WORKINGSET_NODES);

	spin_unlock(lru_lock);

	/*
	 * The nodes should only contain one or more shadow entries,
	 * no pages, so we expect to be able to remove them all and
	 * delete and free the empty node afterwards.
	 */
	if (WARN_ON_ONCE(!node->nr_values))
		goto out_invalid;
	if (WARN_ON_ONCE(node->count != node->nr_values))
		goto out_invalid;
	mapping->nrexceptional -= node->nr_values;
	xas.xa_node = xa_parent_locked(&mapping->i_pages, node);
	xas.xa_offset = node->offset;
	xas.xa_shift = node->shift + XA_CHUNK_SHIFT;
	xas_set_update(&xas, workingset_update_node);
	/*
	 * We could store a shadow entry here which was the minimum of the
	 * shadow entries we were tracking ...
	 */
	xas_store(&xas, NULL);
	__inc_lruvec_slab_state(node, WORKINGSET_NODERECLAIM);

out_invalid:
	xa_unlock_irq(&mapping->i_pages);
	ret = LRU_REMOVED_RETRY;
out:
	cond_resched();
	spin_lock_irq(lru_lock);
	return ret;
}

static unsigned long scan_shadow_nodes(struct shrinker *shrinker,
				       struct shrink_control *sc)
{
	/* list_lru lock nests inside the IRQ-safe i_pages lock */
	return list_lru_shrink_walk_irq(&shadow_nodes, sc, shadow_lru_isolate,
					NULL);
}

static struct shrinker workingset_shadow_shrinker = {
	.count_objects = count_shadow_nodes,
	.scan_objects = scan_shadow_nodes,
	.seeks = 0, /* ->count reports only fully expendable nodes */
	.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE,
};

/*
 * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe
 * i_pages lock.
 */
static struct lock_class_key shadow_nodes_key;

static int __init workingset_init(void)
{
	unsigned int timestamp_bits;
	unsigned int max_order;
	int ret;

	unsigned int lru_gen_timestamp_bits;

	BUILD_BUG_ON(BITS_PER_LONG < EVICTION_SHIFT);
	/*
	 * Calculate the eviction bucket size to cover the longest
	 * actionable refault distance, which is currently half of
	 * memory (totalram_pages/2). However, memory hotplug may add
	 * some more pages at runtime, so keep working with up to
	 * double the initial memory by using totalram_pages as-is.
	 */
	timestamp_bits = BITS_PER_LONG - EVICTION_SHIFT;
	max_order = fls_long(totalram_pages() - 1);
	if (max_order > timestamp_bits)
		bucket_order = max_order - timestamp_bits;

	pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n",
	       timestamp_bits, max_order, bucket_order);

	BUILD_BUG_ON(BITS_PER_LONG < LRU_GEN_EVICTION_SHIFT);
	lru_gen_timestamp_bits = BITS_PER_LONG - LRU_GEN_EVICTION_SHIFT;
	if (max_order > lru_gen_timestamp_bits)
		lru_gen_bucket_order = max_order - timestamp_bits;

	pr_info("workingset: lru_gen_timestamp_bits=%d max_order=%d lru_gen_bucket_order=%u\n",
	       lru_gen_timestamp_bits, max_order, lru_gen_bucket_order);

	ret = prealloc_shrinker(&workingset_shadow_shrinker);
	if (ret)
		goto err;
	ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key,
			      &workingset_shadow_shrinker);
	if (ret)
		goto err_list_lru;
	register_shrinker_prepared(&workingset_shadow_shrinker);
	return 0;
err_list_lru:
	free_prealloced_shrinker(&workingset_shadow_shrinker);
err:
	return ret;
}
module_init(workingset_init);