mm: multi-gen LRU: minimal implementation

To avoid confusion, the terms "promotion" and "demotion" will be applied
to the multi-gen LRU, as a new convention; the terms "activation" and
"deactivation" will be applied to the active/inactive LRU, as usual.

The aging produces young generations.  Given an lruvec, it increments
max_seq when max_seq-min_seq+1 approaches MIN_NR_GENS.  The aging promotes
hot pages to the youngest generation when it finds them accessed through
page tables; the demotion of cold pages happens consequently when it
increments max_seq.  Promotion in the aging path does not involve any LRU
list operations, only the updates of the gen counter and
lrugen->nr_pages[]; demotion, unless as the result of the increment of
max_seq, requires LRU list operations, e.g., lru_deactivate_fn().  The
aging has the complexity O(nr_hot_pages), since it is only interested in
hot pages.

The eviction consumes old generations.  Given an lruvec, it increments
min_seq when lrugen->lists[] indexed by min_seq%MAX_NR_GENS becomes empty.
A feedback loop modeled after the PID controller monitors refaults over
anon and file types and decides which type to evict when both types are
available from the same generation.

The protection of pages accessed multiple times through file descriptors
takes place in the eviction path.  Each generation is divided into
multiple tiers.  A page accessed N times through file descriptors is in
tier order_base_2(N).  Tiers do not have dedicated lrugen->lists[], only
bits in folio->flags.  The aforementioned feedback loop also monitors
refaults over all tiers and decides when to protect pages in which tiers
(N>1), using the first tier (N=0,1) as a baseline.  The first tier
contains single-use unmapped clean pages, which are most likely the best
choices.  In contrast to promotion in the aging path, the protection of a
page in the eviction path is achieved by moving this page to the next
generation, i.e., min_seq+1, if the feedback loop decides so.  This
approach has the following advantages:

1. It removes the cost of activation in the buffered access path by
   inferring whether pages accessed multiple times through file
   descriptors are statistically hot and thus worth protecting in the
   eviction path.
2. It takes pages accessed through page tables into account and avoids
   overprotecting pages accessed multiple times through file
   descriptors. (Pages accessed through page tables are in the first
   tier, since N=0.)
3. More tiers provide better protection for pages accessed more than
   twice through file descriptors, when under heavy buffered I/O
   workloads.

Server benchmark results:
  Single workload:
    fio (buffered I/O): +[30, 32]%
                IOPS         BW
      5.19-rc1: 2673k        10.2GiB/s
      patch1-6: 3491k        13.3GiB/s

  Single workload:
    memcached (anon): -[4, 6]%
                Ops/sec      KB/sec
      5.19-rc1: 1161501.04   45177.25
      patch1-6: 1106168.46   43025.04

  Configurations:
    CPU: two Xeon 6154
    Mem: total 256G

    Node 1 was only used as a ram disk to reduce the variance in the
    results.

    patch drivers/block/brd.c <<EOF
    99,100c99,100
    < 	gfp_flags = GFP_NOIO | __GFP_ZERO | __GFP_HIGHMEM;
    < 	page = alloc_page(gfp_flags);
    ---
    > 	gfp_flags = GFP_NOIO | __GFP_ZERO | __GFP_HIGHMEM | __GFP_THISNODE;
    > 	page = alloc_pages_node(1, gfp_flags, 0);
    EOF

    cat >>/etc/systemd/system.conf <<EOF
    CPUAffinity=numa
    NUMAPolicy=bind
    NUMAMask=0
    EOF

    cat >>/etc/memcached.conf <<EOF
    -m 184320
    -s /var/run/memcached/memcached.sock
    -a 0766
    -t 36
    -B binary
    EOF

    cat fio.sh
    modprobe brd rd_nr=1 rd_size=113246208
    swapoff -a
    mkfs.ext4 /dev/ram0
    mount -t ext4 /dev/ram0 /mnt

    mkdir /sys/fs/cgroup/user.slice/test
    echo 38654705664 >/sys/fs/cgroup/user.slice/test/memory.max
    echo $$ >/sys/fs/cgroup/user.slice/test/cgroup.procs
    fio -name=mglru --numjobs=72 --directory=/mnt --size=1408m \
      --buffered=1 --ioengine=io_uring --iodepth=128 \
      --iodepth_batch_submit=32 --iodepth_batch_complete=32 \
      --rw=randread --random_distribution=random --norandommap \
      --time_based --ramp_time=10m --runtime=5m --group_reporting

    cat memcached.sh
    modprobe brd rd_nr=1 rd_size=113246208
    swapoff -a
    mkswap /dev/ram0
    swapon /dev/ram0

    memtier_benchmark -S /var/run/memcached/memcached.sock \
      -P memcache_binary -n allkeys --key-minimum=1 \
      --key-maximum=65000000 --key-pattern=P:P -c 1 -t 36 \
      --ratio 1:0 --pipeline 8 -d 2000

    memtier_benchmark -S /var/run/memcached/memcached.sock \
      -P memcache_binary -n allkeys --key-minimum=1 \
      --key-maximum=65000000 --key-pattern=R:R -c 1 -t 36 \
      --ratio 0:1 --pipeline 8 --randomize --distinct-client-seed

Client benchmark results:
  kswapd profiles:
    5.19-rc1
      40.33%  page_vma_mapped_walk (overhead)
      21.80%  lzo1x_1_do_compress (real work)
       7.53%  do_raw_spin_lock
       3.95%  _raw_spin_unlock_irq
       2.52%  vma_interval_tree_iter_next
       2.37%  folio_referenced_one
       2.28%  vma_interval_tree_subtree_search
       1.97%  anon_vma_interval_tree_iter_first
       1.60%  ptep_clear_flush
       1.06%  __zram_bvec_write

    patch1-6
      39.03%  lzo1x_1_do_compress (real work)
      18.47%  page_vma_mapped_walk (overhead)
       6.74%  _raw_spin_unlock_irq
       3.97%  do_raw_spin_lock
       2.49%  ptep_clear_flush
       2.48%  anon_vma_interval_tree_iter_first
       1.92%  folio_referenced_one
       1.88%  __zram_bvec_write
       1.48%  memmove
       1.31%  vma_interval_tree_iter_next

  Configurations:
    CPU: single Snapdragon 7c
    Mem: total 4G

    ChromeOS MemoryPressure [1]

[1] https://chromium.googlesource.com/chromiumos/platform/tast-tests/

Link: https://lkml.kernel.org/r/20220918080010.2920238-7-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Acked-by: Brian Geffon <bgeffon@google.com>
Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Acked-by: Steven Barrett <steven@liquorix.net>
Acked-by: Suleiman Souhlal <suleiman@google.com>
Tested-by: Daniel Byrne <djbyrne@mtu.edu>
Tested-by: Donald Carr <d@chaos-reins.com>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
Tested-by: Sofia Trinh <sofia.trinh@edi.works>
Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Larabel <Michael@MichaelLarabel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 784 insertions, 8 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 680ad52090e1..674d336dfe00 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1334,9 +1334,11 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
 
 	if (folio_test_swapcache(folio)) {
 		swp_entry_t swap = folio_swap_entry(folio);
-		mem_cgroup_swapout(folio, swap);
+
+		/* get a shadow entry before mem_cgroup_swapout() clears folio_memcg() */
 		if (reclaimed && !mapping_exiting(mapping))
 			shadow = workingset_eviction(folio, target_memcg);
+		mem_cgroup_swapout(folio, swap);
 		__delete_from_swap_cache(folio, swap, shadow);
 		xa_unlock_irq(&mapping->i_pages);
 		put_swap_page(&folio->page, swap);
@@ -2733,6 +2735,9 @@ static void prepare_scan_count(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);
 
 	/*
@@ -3056,6 +3061,17 @@ static bool can_age_anon_pages(struct pglist_data *pgdat,
  *                          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)++)	\
@@ -3081,6 +3097,745 @@ static struct lruvec __maybe_unused *get_lruvec(struct mem_cgroup *memcg, int ni
 	return pgdat ? &pgdat->__lruvec : NULL;
 }
 
+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 (!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_struct */
+	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;
+}
+
+/******************************************************************************
+ *                          refault feedback loop
+ ******************************************************************************/
+
+/*
+ * 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_struct *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_struct *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
+ ******************************************************************************/
+
+/* 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_struct *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_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 inc_min_seq(struct lruvec *lruvec, int type)
+{
+	struct lru_gen_struct *lrugen = &lruvec->lrugen;
+
+	reset_ctrl_pos(lruvec, type, true);
+	WRITE_ONCE(lrugen->min_seq[type], lrugen->min_seq[type] + 1);
+}
+
+static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap)
+{
+	int gen, type, zone;
+	bool success = false;
+	struct lru_gen_struct *lrugen = &lruvec->lrugen;
+	DEFINE_MIN_SEQ(lruvec);
+
+	VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
+
+	/* find the oldest populated generation */
+	for (type = !can_swap; type < ANON_AND_FILE; type++) {
+		while (min_seq[type] + MIN_NR_GENS <= lrugen->max_seq) {
+			gen = lru_gen_from_seq(min_seq[type]);
+
+			for (zone = 0; zone < MAX_NR_ZONES; zone++) {
+				if (!list_empty(&lrugen->lists[gen][type][zone]))
+					goto next;
+			}
+
+			min_seq[type]++;
+		}
+next:
+		;
+	}
+
+	/* see the comment on lru_gen_struct */
+	if (can_swap) {
+		min_seq[LRU_GEN_ANON] = min(min_seq[LRU_GEN_ANON], min_seq[LRU_GEN_FILE]);
+		min_seq[LRU_GEN_FILE] = max(min_seq[LRU_GEN_ANON], lrugen->min_seq[LRU_GEN_FILE]);
+	}
+
+	for (type = !can_swap; type < ANON_AND_FILE; type++) {
+		if (min_seq[type] == lrugen->min_seq[type])
+			continue;
+
+		reset_ctrl_pos(lruvec, type, true);
+		WRITE_ONCE(lrugen->min_seq[type], min_seq[type]);
+		success = true;
+	}
+
+	return success;
+}
+
+static void inc_max_seq(struct lruvec *lruvec, unsigned long max_seq, bool can_swap)
+{
+	int prev, next;
+	int type, zone;
+	struct lru_gen_struct *lrugen = &lruvec->lrugen;
+
+	spin_lock_irq(&lruvec->lru_lock);
+
+	VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
+
+	if (max_seq != lrugen->max_seq)
+		goto unlock;
+
+	for (type = ANON_AND_FILE - 1; type >= 0; type--) {
+		if (get_nr_gens(lruvec, type) != MAX_NR_GENS)
+			continue;
+
+		VM_WARN_ON_ONCE(type == LRU_GEN_FILE || can_swap);
+
+		inc_min_seq(lruvec, type);
+	}
+
+	/*
+	 * Update the active/inactive LRU sizes for compatibility. Both sides of
+	 * the current max_seq need to be covered, since max_seq+1 can overlap
+	 * with min_seq[LRU_GEN_ANON] if swapping is constrained. And if they do
+	 * overlap, cold/hot inversion happens.
+	 */
+	prev = lru_gen_from_seq(lrugen->max_seq - 1);
+	next = lru_gen_from_seq(lrugen->max_seq + 1);
+
+	for (type = 0; type < ANON_AND_FILE; type++) {
+		for (zone = 0; zone < MAX_NR_ZONES; zone++) {
+			enum lru_list lru = type * LRU_INACTIVE_FILE;
+			long delta = lrugen->nr_pages[prev][type][zone] -
+				     lrugen->nr_pages[next][type][zone];
+
+			if (!delta)
+				continue;
+
+			__update_lru_size(lruvec, lru, zone, delta);
+			__update_lru_size(lruvec, lru + LRU_ACTIVE, zone, -delta);
+		}
+	}
+
+	for (type = 0; type < ANON_AND_FILE; type++)
+		reset_ctrl_pos(lruvec, type, false);
+
+	/* make sure preceding modifications appear */
+	smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1);
+unlock:
+	spin_unlock_irq(&lruvec->lru_lock);
+}
+
+static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, unsigned long *min_seq,
+			     struct scan_control *sc, bool can_swap, unsigned long *nr_to_scan)
+{
+	int gen, type, zone;
+	unsigned long old = 0;
+	unsigned long young = 0;
+	unsigned long total = 0;
+	struct lru_gen_struct *lrugen = &lruvec->lrugen;
+	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+
+	for (type = !can_swap; type < ANON_AND_FILE; type++) {
+		unsigned long seq;
+
+		for (seq = min_seq[type]; seq <= max_seq; seq++) {
+			unsigned long size = 0;
+
+			gen = lru_gen_from_seq(seq);
+
+			for (zone = 0; zone < MAX_NR_ZONES; zone++)
+				size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
+
+			total += size;
+			if (seq == max_seq)
+				young += size;
+			else if (seq + MIN_NR_GENS == max_seq)
+				old += size;
+		}
+	}
+
+	/* try to scrape all its memory if this memcg was deleted */
+	*nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total;
+
+	/*
+	 * The aging tries to be lazy to reduce the overhead, while the eviction
+	 * stalls when the number of generations reaches MIN_NR_GENS. Hence, the
+	 * ideal number of generations is MIN_NR_GENS+1.
+	 */
+	if (min_seq[!can_swap] + MIN_NR_GENS > max_seq)
+		return true;
+	if (min_seq[!can_swap] + MIN_NR_GENS < max_seq)
+		return false;
+
+	/*
+	 * It's also ideal to spread pages out evenly, i.e., 1/(MIN_NR_GENS+1)
+	 * of the total number of pages for each generation. A reasonable range
+	 * for this average portion is [1/MIN_NR_GENS, 1/(MIN_NR_GENS+2)]. The
+	 * aging cares about the upper bound of hot pages, while the eviction
+	 * cares about the lower bound of cold pages.
+	 */
+	if (young * MIN_NR_GENS > total)
+		return true;
+	if (old * (MIN_NR_GENS + 2) < total)
+		return true;
+
+	return false;
+}
+
+static void age_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+{
+	bool need_aging;
+	unsigned long nr_to_scan;
+	int swappiness = get_swappiness(lruvec, sc);
+	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+	DEFINE_MAX_SEQ(lruvec);
+	DEFINE_MIN_SEQ(lruvec);
+
+	VM_WARN_ON_ONCE(sc->memcg_low_reclaim);
+
+	mem_cgroup_calculate_protection(NULL, memcg);
+
+	if (mem_cgroup_below_min(memcg))
+		return;
+
+	need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, swappiness, &nr_to_scan);
+	if (need_aging)
+		inc_max_seq(lruvec, max_seq, swappiness);
+}
+
+static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
+{
+	struct mem_cgroup *memcg;
+
+	VM_WARN_ON_ONCE(!current_is_kswapd());
+
+	memcg = mem_cgroup_iter(NULL, NULL, NULL);
+	do {
+		struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
+
+		age_lruvec(lruvec, sc);
+
+		cond_resched();
+	} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
+}
+
+/******************************************************************************
+ *                          the eviction
+ ******************************************************************************/
+
+static bool sort_folio(struct lruvec *lruvec, struct folio *folio, int tier_idx)
+{
+	bool success;
+	int gen = folio_lru_gen(folio);
+	int type = folio_is_file_lru(folio);
+	int zone = folio_zonenum(folio);
+	int delta = folio_nr_pages(folio);
+	int refs = folio_lru_refs(folio);
+	int tier = lru_tier_from_refs(refs);
+	struct lru_gen_struct *lrugen = &lruvec->lrugen;
+
+	VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio);
+
+	/* unevictable */
+	if (!folio_evictable(folio)) {
+		success = lru_gen_del_folio(lruvec, folio, true);
+		VM_WARN_ON_ONCE_FOLIO(!success, folio);
+		folio_set_unevictable(folio);
+		lruvec_add_folio(lruvec, folio);
+		__count_vm_events(UNEVICTABLE_PGCULLED, delta);
+		return true;
+	}
+
+	/* dirty lazyfree */
+	if (type == LRU_GEN_FILE && folio_test_anon(folio) && folio_test_dirty(folio)) {
+		success = lru_gen_del_folio(lruvec, folio, true);
+		VM_WARN_ON_ONCE_FOLIO(!success, folio);
+		folio_set_swapbacked(folio);
+		lruvec_add_folio_tail(lruvec, folio);
+		return true;
+	}
+
+	/* protected */
+	if (tier > tier_idx) {
+		int hist = lru_hist_from_seq(lrugen->min_seq[type]);
+
+		gen = folio_inc_gen(lruvec, folio, false);
+		list_move_tail(&folio->lru, &lrugen->lists[gen][type][zone]);
+
+		WRITE_ONCE(lrugen->protected[hist][type][tier - 1],
+			   lrugen->protected[hist][type][tier - 1] + delta);
+		__mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta);
+		return true;
+	}
+
+	/* waiting for writeback */
+	if (folio_test_locked(folio) || folio_test_writeback(folio) ||
+	    (type == LRU_GEN_FILE && folio_test_dirty(folio))) {
+		gen = folio_inc_gen(lruvec, folio, true);
+		list_move(&folio->lru, &lrugen->lists[gen][type][zone]);
+		return true;
+	}
+
+	return false;
+}
+
+static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc)
+{
+	bool success;
+
+	/* unmapping inhibited */
+	if (!sc->may_unmap && folio_mapped(folio))
+		return false;
+
+	/* swapping inhibited */
+	if (!(sc->may_writepage && (sc->gfp_mask & __GFP_IO)) &&
+	    (folio_test_dirty(folio) ||
+	     (folio_test_anon(folio) && !folio_test_swapcache(folio))))
+		return false;
+
+	/* raced with release_pages() */
+	if (!folio_try_get(folio))
+		return false;
+
+	/* raced with another isolation */
+	if (!folio_test_clear_lru(folio)) {
+		folio_put(folio);
+		return false;
+	}
+
+	/* see the comment on MAX_NR_TIERS */
+	if (!folio_test_referenced(folio))
+		set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0);
+
+	/* for shrink_page_list() */
+	folio_clear_reclaim(folio);
+	folio_clear_referenced(folio);
+
+	success = lru_gen_del_folio(lruvec, folio, true);
+	VM_WARN_ON_ONCE_FOLIO(!success, folio);
+
+	return true;
+}
+
+static int scan_folios(struct lruvec *lruvec, struct scan_control *sc,
+		       int type, int tier, struct list_head *list)
+{
+	int gen, zone;
+	enum vm_event_item item;
+	int sorted = 0;
+	int scanned = 0;
+	int isolated = 0;
+	int remaining = MAX_LRU_BATCH;
+	struct lru_gen_struct *lrugen = &lruvec->lrugen;
+	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+
+	VM_WARN_ON_ONCE(!list_empty(list));
+
+	if (get_nr_gens(lruvec, type) == MIN_NR_GENS)
+		return 0;
+
+	gen = lru_gen_from_seq(lrugen->min_seq[type]);
+
+	for (zone = sc->reclaim_idx; zone >= 0; zone--) {
+		LIST_HEAD(moved);
+		int skipped = 0;
+		struct list_head *head = &lrugen->lists[gen][type][zone];
+
+		while (!list_empty(head)) {
+			struct folio *folio = lru_to_folio(head);
+			int delta = folio_nr_pages(folio);
+
+			VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio);
+			VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio);
+			VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio);
+			VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio);
+
+			scanned += delta;
+
+			if (sort_folio(lruvec, folio, tier))
+				sorted += delta;
+			else if (isolate_folio(lruvec, folio, sc)) {
+				list_add(&folio->lru, list);
+				isolated += delta;
+			} else {
+				list_move(&folio->lru, &moved);
+				skipped += delta;
+			}
+
+			if (!--remaining || max(isolated, skipped) >= MIN_LRU_BATCH)
+				break;
+		}
+
+		if (skipped) {
+			list_splice(&moved, head);
+			__count_zid_vm_events(PGSCAN_SKIP, zone, skipped);
+		}
+
+		if (!remaining || isolated >= MIN_LRU_BATCH)
+			break;
+	}
+
+	item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT;
+	if (!cgroup_reclaim(sc)) {
+		__count_vm_events(item, isolated);
+		__count_vm_events(PGREFILL, sorted);
+	}
+	__count_memcg_events(memcg, item, isolated);
+	__count_memcg_events(memcg, PGREFILL, sorted);
+	__count_vm_events(PGSCAN_ANON + type, isolated);
+
+	/*
+	 * There might not be eligible pages due to reclaim_idx, may_unmap and
+	 * may_writepage. Check the remaining to prevent livelock if it's not
+	 * making progress.
+	 */
+	return isolated || !remaining ? scanned : 0;
+}
+
+static int get_tier_idx(struct lruvec *lruvec, int type)
+{
+	int tier;
+	struct ctrl_pos sp, pv;
+
+	/*
+	 * To leave a margin for fluctuations, use a larger gain factor (1:2).
+	 * This value is chosen because any other tier would have at least twice
+	 * as many refaults as the first tier.
+	 */
+	read_ctrl_pos(lruvec, type, 0, 1, &sp);
+	for (tier = 1; tier < MAX_NR_TIERS; tier++) {
+		read_ctrl_pos(lruvec, type, tier, 2, &pv);
+		if (!positive_ctrl_err(&sp, &pv))
+			break;
+	}
+
+	return tier - 1;
+}
+
+static int get_type_to_scan(struct lruvec *lruvec, int swappiness, int *tier_idx)
+{
+	int type, tier;
+	struct ctrl_pos sp, pv;
+	int gain[ANON_AND_FILE] = { swappiness, 200 - swappiness };
+
+	/*
+	 * Compare the first tier of anon with that of file to determine which
+	 * type to scan. Also need to compare other tiers of the selected type
+	 * with the first tier of the other type to determine the last tier (of
+	 * the selected type) to evict.
+	 */
+	read_ctrl_pos(lruvec, LRU_GEN_ANON, 0, gain[LRU_GEN_ANON], &sp);
+	read_ctrl_pos(lruvec, LRU_GEN_FILE, 0, gain[LRU_GEN_FILE], &pv);
+	type = positive_ctrl_err(&sp, &pv);
+
+	read_ctrl_pos(lruvec, !type, 0, gain[!type], &sp);
+	for (tier = 1; tier < MAX_NR_TIERS; tier++) {
+		read_ctrl_pos(lruvec, type, tier, gain[type], &pv);
+		if (!positive_ctrl_err(&sp, &pv))
+			break;
+	}
+
+	*tier_idx = tier - 1;
+
+	return type;
+}
+
+static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
+			  int *type_scanned, struct list_head *list)
+{
+	int i;
+	int type;
+	int scanned;
+	int tier = -1;
+	DEFINE_MIN_SEQ(lruvec);
+
+	/*
+	 * Try to make the obvious choice first. When anon and file are both
+	 * available from the same generation, interpret swappiness 1 as file
+	 * first and 200 as anon first.
+	 */
+	if (!swappiness)
+		type = LRU_GEN_FILE;
+	else if (min_seq[LRU_GEN_ANON] < min_seq[LRU_GEN_FILE])
+		type = LRU_GEN_ANON;
+	else if (swappiness == 1)
+		type = LRU_GEN_FILE;
+	else if (swappiness == 200)
+		type = LRU_GEN_ANON;
+	else
+		type = get_type_to_scan(lruvec, swappiness, &tier);
+
+	for (i = !swappiness; i < ANON_AND_FILE; i++) {
+		if (tier < 0)
+			tier = get_tier_idx(lruvec, type);
+
+		scanned = scan_folios(lruvec, sc, type, tier, list);
+		if (scanned)
+			break;
+
+		type = !type;
+		tier = -1;
+	}
+
+	*type_scanned = type;
+
+	return scanned;
+}
+
+static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
+{
+	int type;
+	int scanned;
+	int reclaimed;
+	LIST_HEAD(list);
+	struct folio *folio;
+	enum vm_event_item item;
+	struct reclaim_stat stat;
+	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+
+	spin_lock_irq(&lruvec->lru_lock);
+
+	scanned = isolate_folios(lruvec, sc, swappiness, &type, &list);
+
+	scanned += try_to_inc_min_seq(lruvec, swappiness);
+
+	if (get_nr_gens(lruvec, !swappiness) == MIN_NR_GENS)
+		scanned = 0;
+
+	spin_unlock_irq(&lruvec->lru_lock);
+
+	if (list_empty(&list))
+		return scanned;
+
+	reclaimed = shrink_page_list(&list, pgdat, sc, &stat, false);
+
+	list_for_each_entry(folio, &list, lru) {
+		/* restore LRU_REFS_FLAGS cleared by isolate_folio() */
+		if (folio_test_workingset(folio))
+			folio_set_referenced(folio);
+
+		/* don't add rejected pages to the oldest generation */
+		if (folio_test_reclaim(folio) &&
+		    (folio_test_dirty(folio) || folio_test_writeback(folio)))
+			folio_clear_active(folio);
+		else
+			folio_set_active(folio);
+	}
+
+	spin_lock_irq(&lruvec->lru_lock);
+
+	move_pages_to_lru(lruvec, &list);
+
+	item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
+	if (!cgroup_reclaim(sc))
+		__count_vm_events(item, reclaimed);
+	__count_memcg_events(memcg, item, reclaimed);
+	__count_vm_events(PGSTEAL_ANON + type, reclaimed);
+
+	spin_unlock_irq(&lruvec->lru_lock);
+
+	mem_cgroup_uncharge_list(&list);
+	free_unref_page_list(&list);
+
+	sc->nr_reclaimed += reclaimed;
+
+	return scanned;
+}
+
+static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc,
+				    bool can_swap)
+{
+	bool need_aging;
+	unsigned long nr_to_scan;
+	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+	DEFINE_MAX_SEQ(lruvec);
+	DEFINE_MIN_SEQ(lruvec);
+
+	if (mem_cgroup_below_min(memcg) ||
+	    (mem_cgroup_below_low(memcg) && !sc->memcg_low_reclaim))
+		return 0;
+
+	need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, can_swap, &nr_to_scan);
+	if (!need_aging)
+		return nr_to_scan;
+
+	/* skip the aging path at the default priority */
+	if (sc->priority == DEF_PRIORITY)
+		goto done;
+
+	/* leave the work to lru_gen_age_node() */
+	if (current_is_kswapd())
+		return 0;
+
+	inc_max_seq(lruvec, max_seq, can_swap);
+done:
+	return min_seq[!can_swap] + MIN_NR_GENS <= max_seq ? nr_to_scan : 0;
+}
+
+static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+{
+	struct blk_plug plug;
+	unsigned long scanned = 0;
+
+	lru_add_drain();
+
+	blk_start_plug(&plug);
+
+	while (true) {
+		int delta;
+		int swappiness;
+		unsigned long nr_to_scan;
+
+		if (sc->may_swap)
+			swappiness = get_swappiness(lruvec, sc);
+		else if (!cgroup_reclaim(sc) && get_swappiness(lruvec, sc))
+			swappiness = 1;
+		else
+			swappiness = 0;
+
+		nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness);
+		if (!nr_to_scan)
+			break;
+
+		delta = evict_folios(lruvec, sc, swappiness);
+		if (!delta)
+			break;
+
+		scanned += delta;
+		if (scanned >= nr_to_scan)
+			break;
+
+		cond_resched();
+	}
+
+	blk_finish_plug(&plug);
+}
+
 /******************************************************************************
  *                          initialization
  ******************************************************************************/
@@ -3123,6 +3878,16 @@ static int __init init_lru_gen(void)
 };
 late_initcall(init_lru_gen);
 
+#else /* !CONFIG_LRU_GEN */
+
+static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
+{
+}
+
+static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+{
+}
+
 #endif /* CONFIG_LRU_GEN */
 
 static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
@@ -3136,6 +3901,11 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 	struct blk_plug plug;
 	bool scan_adjusted;
 
+	if (lru_gen_enabled()) {
+		lru_gen_shrink_lruvec(lruvec, sc);
+		return;
+	}
+
 	get_scan_count(lruvec, sc, nr);
 
 	/* Record the original scan target for proportional adjustments later */
@@ -3642,6 +4412,9 @@ static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat)
 	struct lruvec *target_lruvec;
 	unsigned long refaults;
 
+	if (lru_gen_enabled())
+		return;
+
 	target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
 	refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON);
 	target_lruvec->refaults[WORKINGSET_ANON] = refaults;
@@ -4008,12 +4781,16 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 }
 #endif
 
-static void age_active_anon(struct pglist_data *pgdat,
-				struct scan_control *sc)
+static void kswapd_age_node(struct pglist_data *pgdat, struct scan_control *sc)
 {
 	struct mem_cgroup *memcg;
 	struct lruvec *lruvec;
 
+	if (lru_gen_enabled()) {
+		lru_gen_age_node(pgdat, sc);
+		return;
+	}
+
 	if (!can_age_anon_pages(pgdat, sc))
 		return;
 
@@ -4333,12 +5110,11 @@ restart:
 		sc.may_swap = !nr_boost_reclaim;
 
 		/*
-		 * Do some background aging of the anon list, to give
-		 * pages a chance to be referenced before reclaiming. All
-		 * pages are rotated regardless of classzone as this is
-		 * about consistent aging.
+		 * Do some background aging, to give pages a chance to be
+		 * referenced before reclaiming. All pages are rotated
+		 * regardless of classzone as this is about consistent aging.
 		 */
-		age_active_anon(pgdat, &sc);
+		kswapd_age_node(pgdat, &sc);
 
 		/*
 		 * If we're getting trouble reclaiming, start doing writepage