Re: [PATCH 3/8] mm/mglru: restructure the reclaim loop

[Axel Rasmussen <axelrasmussen@google.com>]

This looks like a reasonable refactor to me. To me the new code is
more straightforward to reason about, and I don't see anything this
breaks (either by inspection of with basic functional testing).

Reviewed-by: Axel Rasmussen <axelrasmussen@google.com>

On Tue, Mar 17, 2026 at 12:11 PM Kairui Song via B4 Relay
<devnull+kasong.tencent.com@kernel.org> wrote:
>
> From: Kairui Song <kasong@tencent.com>
>
> The current loop will calculate the scan number on each iteration. The
> number of folios to scan is based on the LRU length, with some unclear
> behaviors, eg, it only shifts the scan number by reclaim priority at the
> default priority, and it couples the number calculation with aging and
> rotation.
>
> Adjust, simplify it, and decouple aging and rotation. Just calculate the
> scan number for once at the beginning of the reclaim, always respect the
> reclaim priority, and make the aging and rotation more explicit.
>
> This slightly changes how offline memcg aging works: previously, offline
> memcg wouldn't be aged unless it didn't have any evictable folios. Now,
> we might age it if it has only 3 generations and the reclaim priority is
> less than DEF_PRIORITY, which should be fine. On one hand, offline memcg
> might still hold long-term folios, and in fact, a long-existing offline
> memcg must be pinned by some long-term folios like shmem. These folios
> might be used by other memcg, so aging them as ordinary memcg doesn't
> seem wrong. And besides, aging enables further reclaim of an offlined
> memcg, which will certainly happen if we keep shrinking it. And offline
> memcg might soon be no longer an issue once reparenting is all ready.
>
> Overall, the memcg LRU rotation, as described in mmzone.h,
> remains the same.
>
> Signed-off-by: Kairui Song <kasong@tencent.com>
> ---
>  mm/vmscan.c | 74 ++++++++++++++++++++++++++++++-------------------------------
>  1 file changed, 36 insertions(+), 38 deletions(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index d48074f9bd87..ed5b5f8dd3c7 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -4926,49 +4926,35 @@ static int evict_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
>  }
>
>  static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
> -                            int swappiness, unsigned long *nr_to_scan)
> +                            struct scan_control *sc, int swappiness)
>  {
>         DEFINE_MIN_SEQ(lruvec);
>
> -       *nr_to_scan = 0;
>         /* have to run aging, since eviction is not possible anymore */
>         if (evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS > max_seq)
>                 return true;
>
> -       *nr_to_scan = lruvec_evictable_size(lruvec, swappiness);
> +       /* try to get away with not aging at the default priority */
> +       if (sc->priority == DEF_PRIORITY)
> +               return false;
> +
>         /* better to run aging even though eviction is still possible */
>         return evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS == max_seq;
>  }
>
> -/*
> - * For future optimizations:
> - * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg
> - *    reclaim.
> - */
> -static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
> +static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc,
> +                          struct mem_cgroup *memcg, int swappiness)
>  {
> -       bool need_aging;
>         unsigned long nr_to_scan;
> -       struct mem_cgroup *memcg = lruvec_memcg(lruvec);
> -       DEFINE_MAX_SEQ(lruvec);
> -
> -       if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg))
> -               return -1;
> -
> -       need_aging = should_run_aging(lruvec, max_seq, swappiness, &nr_to_scan);
>
> +       nr_to_scan = lruvec_evictable_size(lruvec, swappiness);
>         /* try to scrape all its memory if this memcg was deleted */
> -       if (nr_to_scan && !mem_cgroup_online(memcg))
> +       if (!mem_cgroup_online(memcg))
>                 return nr_to_scan;
>
>         nr_to_scan = apply_proportional_protection(memcg, sc, nr_to_scan);
> -
> -       /* try to get away with not aging at the default priority */
> -       if (!need_aging || sc->priority == DEF_PRIORITY)
> -               return nr_to_scan >> sc->priority;
> -
> -       /* stop scanning this lruvec as it's low on cold folios */
> -       return try_to_inc_max_seq(lruvec, max_seq, swappiness, false) ? -1 : 0;
> +       /* always respect scan priority */
> +       return nr_to_scan >> sc->priority;
>  }
>
>  static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc)
> @@ -4998,31 +4984,43 @@ static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc)
>         return true;
>  }
>
> +/*
> + * For future optimizations:
> + * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg
> + *    reclaim.
> + */
>  static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
>  {
> +       bool need_rotate = false;
>         long nr_batch, nr_to_scan;
> -       unsigned long scanned = 0;
>         int swappiness = get_swappiness(lruvec, sc);
> +       struct mem_cgroup *memcg = lruvec_memcg(lruvec);
>
> -       while (true) {
> +       nr_to_scan = get_nr_to_scan(lruvec, sc, memcg, swappiness);
> +       while (nr_to_scan > 0) {
>                 int delta;
> +               DEFINE_MAX_SEQ(lruvec);
>
> -               nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness);
> -               if (nr_to_scan <= 0)
> +               if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg)) {
> +                       need_rotate = true;
>                         break;
> +               }
> +
> +               if (should_run_aging(lruvec, max_seq, sc, swappiness)) {
> +                       if (try_to_inc_max_seq(lruvec, max_seq, swappiness, false))
> +                               need_rotate = true;
> +                       break;
> +               }
>
>                 nr_batch = min(nr_to_scan, MAX_LRU_BATCH);
>                 delta = evict_folios(nr_batch, lruvec, sc, swappiness);
>                 if (!delta)
>                         break;
>
> -               scanned += delta;
> -               if (scanned >= nr_to_scan)
> -                       break;
> -
>                 if (should_abort_scan(lruvec, sc))
>                         break;
>
> +               nr_to_scan -= delta;
>                 cond_resched();
>         }
>
> @@ -5034,12 +5032,12 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
>                 wakeup_flusher_threads(WB_REASON_VMSCAN);
>
>         /* whether this lruvec should be rotated */

It's a nitpick, but with the variable rename, this comment isn't doing
is much good now. :)

> -       return nr_to_scan < 0;
> +       return need_rotate;
>  }
>
>  static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
>  {
> -       bool success;
> +       bool need_rotate;
>         unsigned long scanned = sc->nr_scanned;
>         unsigned long reclaimed = sc->nr_reclaimed;
>         struct mem_cgroup *memcg = lruvec_memcg(lruvec);
> @@ -5057,7 +5055,7 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
>                 memcg_memory_event(memcg, MEMCG_LOW);
>         }
>
> -       success = try_to_shrink_lruvec(lruvec, sc);
> +       need_rotate = try_to_shrink_lruvec(lruvec, sc);
>
>         shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority);
>
> @@ -5067,10 +5065,10 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
>
>         flush_reclaim_state(sc);
>
> -       if (success && mem_cgroup_online(memcg))
> +       if (need_rotate && mem_cgroup_online(memcg))
>                 return MEMCG_LRU_YOUNG;
>
> -       if (!success && lruvec_is_sizable(lruvec, sc))
> +       if (!need_rotate && lruvec_is_sizable(lruvec, sc))
>                 return 0;
>
>         /* one retry if offlined or too small */
>
> --
> 2.53.0
>
>