diff options
Diffstat (limited to '')
| -rw-r--r-- | mm/vmscan.c | 5779 |
1 files changed, 4577 insertions, 1202 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c index 876370565455..04d8b88e5216 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 /* - * linux/mm/vmscan.c - * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * * Swap reorganised 29.12.95, Stephen Tweedie. @@ -28,8 +26,7 @@ #include <linux/file.h> #include <linux/writeback.h> #include <linux/blkdev.h> -#include <linux/buffer_head.h> /* for try_to_release_page(), - buffer_heads_over_limit */ +#include <linux/buffer_head.h> /* for buffer_heads_over_limit */ #include <linux/mm_inline.h> #include <linux/backing-dev.h> #include <linux/rmap.h> @@ -43,22 +40,30 @@ #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 <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> @@ -79,7 +84,13 @@ struct scan_control { */ struct mem_cgroup *target_mem_cgroup; - /* Can active pages be deactivated as part of reclaim? */ + /* + * 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; @@ -89,16 +100,22 @@ struct scan_control { /* Writepage batching in laptop mode; RECLAIM_WRITE */ unsigned int may_writepage:1; - /* Can mapped pages be reclaimed? */ + /* Can mapped folios be reclaimed? */ unsigned int may_unmap:1; - /* Can pages be swapped as part of reclaim? */ + /* Can folios be swapped as part of reclaim? */ unsigned int may_swap:1; + /* Proactive reclaim invoked by userspace through memory.reclaim */ + unsigned int proactive:1; + /* - * Cgroups are not reclaimed below their configured memory.low, - * unless we threaten to OOM. If any cgroups are skipped due to - * memory.low and nothing was reclaimed, go back for memory.low. + * 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; @@ -111,16 +128,25 @@ struct scan_control { /* There is easily reclaimable cold cache in the current node */ unsigned int cache_trim_mode:1; - /* The file pages on the current node are dangerously low */ + /* 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; + +#ifdef CONFIG_LRU_GEN + /* help kswapd make better choices among multiple memcgs */ + unsigned int memcgs_need_aging:1; + unsigned long last_reclaimed; +#endif + /* Allocation order */ s8 order; /* Scan (total_size >> priority) pages at once */ s8 priority; - /* The highest zone to isolate pages for reclaim from */ + /* The highest zone to isolate folios for reclaim from */ s8 reclaim_idx; /* This context's GFP mask */ @@ -147,28 +173,23 @@ struct scan_control { }; #ifdef ARCH_HAS_PREFETCHW -#define prefetchw_prev_lru_page(_page, _base, _field) \ +#define prefetchw_prev_lru_folio(_folio, _base, _field) \ do { \ - if ((_page)->lru.prev != _base) { \ - struct page *prev; \ + if ((_folio)->lru.prev != _base) { \ + struct folio *prev; \ \ - prev = lru_to_page(&(_page->lru)); \ + prev = lru_to_folio(&(_folio->lru)); \ prefetchw(&prev->_field); \ } \ } while (0) #else -#define prefetchw_prev_lru_page(_page, _base, _field) do { } while (0) +#define prefetchw_prev_lru_folio(_folio, _base, _field) do { } while (0) #endif /* - * From 0 .. 100. Higher means more swappy. + * From 0 .. 200. Higher means more swappy. */ int vm_swappiness = 60; -/* - * The total number of pages which are beyond the high watermark within all - * zones. - */ -unsigned long vm_total_pages; static void set_task_reclaim_state(struct task_struct *task, struct reclaim_state *rs) @@ -182,43 +203,185 @@ static void set_task_reclaim_state(struct task_struct *task, task->reclaim_state = rs; } -static LIST_HEAD(shrinker_list); -static DECLARE_RWSEM(shrinker_rwsem); +LIST_HEAD(shrinker_list); +DECLARE_RWSEM(shrinker_rwsem); #ifdef CONFIG_MEMCG -/* - * We allow subsystems to populate their shrinker-related - * LRU lists before register_shrinker_prepared() is called - * for the shrinker, since we don't want to impose - * restrictions on their internal registration order. - * In this case shrink_slab_memcg() may find corresponding - * bit is set in the shrinkers map. - * - * This value is used by the function to detect registering - * shrinkers and to skip do_shrink_slab() calls for them. - */ -#define SHRINKER_REGISTERING ((struct shrinker *)~0UL) +static int shrinker_nr_max; + +/* The shrinker_info is expanded in a batch of BITS_PER_LONG */ +static inline int shrinker_map_size(int nr_items) +{ + return (DIV_ROUND_UP(nr_items, BITS_PER_LONG) * sizeof(unsigned long)); +} + +static inline int shrinker_defer_size(int nr_items) +{ + return (round_up(nr_items, BITS_PER_LONG) * sizeof(atomic_long_t)); +} + +static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, + int nid) +{ + return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, + lockdep_is_held(&shrinker_rwsem)); +} + +static int expand_one_shrinker_info(struct mem_cgroup *memcg, + int map_size, int defer_size, + int old_map_size, int old_defer_size) +{ + struct shrinker_info *new, *old; + struct mem_cgroup_per_node *pn; + int nid; + int size = map_size + defer_size; + + for_each_node(nid) { + pn = memcg->nodeinfo[nid]; + old = shrinker_info_protected(memcg, nid); + /* Not yet online memcg */ + if (!old) + return 0; + + new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid); + if (!new) + return -ENOMEM; + + new->nr_deferred = (atomic_long_t *)(new + 1); + new->map = (void *)new->nr_deferred + defer_size; + + /* map: set all old bits, clear all new bits */ + memset(new->map, (int)0xff, old_map_size); + memset((void *)new->map + old_map_size, 0, map_size - old_map_size); + /* nr_deferred: copy old values, clear all new values */ + memcpy(new->nr_deferred, old->nr_deferred, old_defer_size); + memset((void *)new->nr_deferred + old_defer_size, 0, + defer_size - old_defer_size); + + rcu_assign_pointer(pn->shrinker_info, new); + kvfree_rcu(old, rcu); + } + + return 0; +} + +void free_shrinker_info(struct mem_cgroup *memcg) +{ + struct mem_cgroup_per_node *pn; + struct shrinker_info *info; + int nid; + + for_each_node(nid) { + pn = memcg->nodeinfo[nid]; + info = rcu_dereference_protected(pn->shrinker_info, true); + kvfree(info); + rcu_assign_pointer(pn->shrinker_info, NULL); + } +} + +int alloc_shrinker_info(struct mem_cgroup *memcg) +{ + struct shrinker_info *info; + int nid, size, ret = 0; + int map_size, defer_size = 0; + + down_write(&shrinker_rwsem); + map_size = shrinker_map_size(shrinker_nr_max); + defer_size = shrinker_defer_size(shrinker_nr_max); + size = map_size + defer_size; + for_each_node(nid) { + info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid); + if (!info) { + free_shrinker_info(memcg); + ret = -ENOMEM; + break; + } + info->nr_deferred = (atomic_long_t *)(info + 1); + info->map = (void *)info->nr_deferred + defer_size; + rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); + } + up_write(&shrinker_rwsem); + + return ret; +} + +static inline bool need_expand(int nr_max) +{ + return round_up(nr_max, BITS_PER_LONG) > + round_up(shrinker_nr_max, BITS_PER_LONG); +} + +static int expand_shrinker_info(int new_id) +{ + int ret = 0; + int new_nr_max = new_id + 1; + int map_size, defer_size = 0; + int old_map_size, old_defer_size = 0; + struct mem_cgroup *memcg; + + if (!need_expand(new_nr_max)) + goto out; + + if (!root_mem_cgroup) + goto out; + + lockdep_assert_held(&shrinker_rwsem); + + map_size = shrinker_map_size(new_nr_max); + defer_size = shrinker_defer_size(new_nr_max); + old_map_size = shrinker_map_size(shrinker_nr_max); + old_defer_size = shrinker_defer_size(shrinker_nr_max); + + memcg = mem_cgroup_iter(NULL, NULL, NULL); + do { + ret = expand_one_shrinker_info(memcg, map_size, defer_size, + old_map_size, old_defer_size); + if (ret) { + mem_cgroup_iter_break(NULL, memcg); + goto out; + } + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); +out: + if (!ret) + shrinker_nr_max = new_nr_max; + + return ret; +} + +void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) +{ + if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { + struct shrinker_info *info; + + rcu_read_lock(); + info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); + /* Pairs with smp mb in shrink_slab() */ + smp_mb__before_atomic(); + set_bit(shrinker_id, info->map); + rcu_read_unlock(); + } +} static DEFINE_IDR(shrinker_idr); -static int shrinker_nr_max; static int prealloc_memcg_shrinker(struct shrinker *shrinker) { int id, ret = -ENOMEM; + if (mem_cgroup_disabled()) + return -ENOSYS; + down_write(&shrinker_rwsem); /* This may call shrinker, so it must use down_read_trylock() */ - id = idr_alloc(&shrinker_idr, SHRINKER_REGISTERING, 0, 0, GFP_KERNEL); + id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); if (id < 0) goto unlock; if (id >= shrinker_nr_max) { - if (memcg_expand_shrinker_maps(id)) { + if (expand_shrinker_info(id)) { idr_remove(&shrinker_idr, id); goto unlock; } - - shrinker_nr_max = id + 1; } shrinker->id = id; ret = 0; @@ -233,9 +396,51 @@ static void unregister_memcg_shrinker(struct shrinker *shrinker) BUG_ON(id < 0); - down_write(&shrinker_rwsem); + lockdep_assert_held(&shrinker_rwsem); + idr_remove(&shrinker_idr, id); - up_write(&shrinker_rwsem); +} + +static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + struct shrinker_info *info; + + info = shrinker_info_protected(memcg, nid); + return atomic_long_xchg(&info->nr_deferred[shrinker->id], 0); +} + +static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + struct shrinker_info *info; + + info = shrinker_info_protected(memcg, nid); + return atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]); +} + +void reparent_shrinker_deferred(struct mem_cgroup *memcg) +{ + int i, nid; + long nr; + struct mem_cgroup *parent; + struct shrinker_info *child_info, *parent_info; + + parent = parent_mem_cgroup(memcg); + if (!parent) + parent = root_mem_cgroup; + + /* Prevent from concurrent shrinker_info expand */ + down_read(&shrinker_rwsem); + for_each_node(nid) { + child_info = shrinker_info_protected(memcg, nid); + parent_info = shrinker_info_protected(parent, nid); + for (i = 0; i < shrinker_nr_max; i++) { + nr = atomic_long_read(&child_info->nr_deferred[i]); + atomic_long_add(nr, &parent_info->nr_deferred[i]); + } + } + up_read(&shrinker_rwsem); } static bool cgroup_reclaim(struct scan_control *sc) @@ -249,7 +454,7 @@ static bool cgroup_reclaim(struct scan_control *sc) * * The normal page dirty throttling mechanism in balance_dirty_pages() is * completely broken with the legacy memcg and direct stalling in - * shrink_page_list() is used for throttling instead, which lacks all the + * shrink_folio_list() is used for throttling instead, which lacks all the * niceties such as fairness, adaptive pausing, bandwidth proportional * allocation and configurability. * @@ -269,13 +474,25 @@ static bool writeback_throttling_sane(struct scan_control *sc) #else static int prealloc_memcg_shrinker(struct shrinker *shrinker) { - return 0; + return -ENOSYS; } static void unregister_memcg_shrinker(struct shrinker *shrinker) { } +static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + return 0; +} + +static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + return 0; +} + static bool cgroup_reclaim(struct scan_control *sc) { return false; @@ -287,10 +504,80 @@ static bool writeback_throttling_sane(struct scan_control *sc) } #endif +static long xchg_nr_deferred(struct shrinker *shrinker, + struct shrink_control *sc) +{ + int nid = sc->nid; + + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) + nid = 0; + + if (sc->memcg && + (shrinker->flags & SHRINKER_MEMCG_AWARE)) + return xchg_nr_deferred_memcg(nid, shrinker, + sc->memcg); + + return atomic_long_xchg(&shrinker->nr_deferred[nid], 0); +} + + +static long add_nr_deferred(long nr, struct shrinker *shrinker, + struct shrink_control *sc) +{ + int nid = sc->nid; + + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) + nid = 0; + + if (sc->memcg && + (shrinker->flags & SHRINKER_MEMCG_AWARE)) + return add_nr_deferred_memcg(nr, nid, shrinker, + sc->memcg); + + return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]); +} + +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 pages which are not accounted for to save counters. + * 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 pages will be a dominating factor. + * not expected that isolated folios will be a dominating factor. */ unsigned long zone_reclaimable_pages(struct zone *zone) { @@ -298,7 +585,7 @@ unsigned long zone_reclaimable_pages(struct zone *zone) nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); - if (get_nr_swap_pages() > 0) + 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); @@ -309,14 +596,15 @@ unsigned long zone_reclaimable_pages(struct zone *zone) * 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 for the whole LRU list) + * @zone_idx: zones to consider (use MAX_NR_ZONES - 1 for the whole LRU list) */ -unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) +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 < MAX_NR_ZONES; zid++) { + for (zid = 0; zid <= zone_idx; zid++) { struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid]; if (!managed_zone(zone)) @@ -333,10 +621,20 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone /* * Add a shrinker callback to be called from the vm. */ -int prealloc_shrinker(struct shrinker *shrinker) +static int __prealloc_shrinker(struct shrinker *shrinker) { - unsigned int size = sizeof(*shrinker->nr_deferred); + unsigned int size; + int err; + + if (shrinker->flags & SHRINKER_MEMCG_AWARE) { + err = prealloc_memcg_shrinker(shrinker); + if (err != -ENOSYS) + return err; + shrinker->flags &= ~SHRINKER_MEMCG_AWARE; + } + + size = sizeof(*shrinker->nr_deferred); if (shrinker->flags & SHRINKER_NUMA_AWARE) size *= nr_node_ids; @@ -344,26 +642,48 @@ int prealloc_shrinker(struct shrinker *shrinker) if (!shrinker->nr_deferred) return -ENOMEM; - if (shrinker->flags & SHRINKER_MEMCG_AWARE) { - if (prealloc_memcg_shrinker(shrinker)) - goto free_deferred; - } - return 0; +} -free_deferred: - kfree(shrinker->nr_deferred); - shrinker->nr_deferred = NULL; - return -ENOMEM; +#ifdef CONFIG_SHRINKER_DEBUG +int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + va_list ap; + int err; + + va_start(ap, fmt); + shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); + va_end(ap); + if (!shrinker->name) + return -ENOMEM; + + err = __prealloc_shrinker(shrinker); + if (err) { + kfree_const(shrinker->name); + shrinker->name = NULL; + } + + return err; +} +#else +int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + return __prealloc_shrinker(shrinker); } +#endif void free_prealloced_shrinker(struct shrinker *shrinker) { - if (!shrinker->nr_deferred) - return; - - if (shrinker->flags & SHRINKER_MEMCG_AWARE) +#ifdef CONFIG_SHRINKER_DEBUG + kfree_const(shrinker->name); + shrinker->name = NULL; +#endif + if (shrinker->flags & SHRINKER_MEMCG_AWARE) { + down_write(&shrinker_rwsem); unregister_memcg_shrinker(shrinker); + up_write(&shrinker_rwsem); + return; + } kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; @@ -373,22 +693,46 @@ void register_shrinker_prepared(struct shrinker *shrinker) { down_write(&shrinker_rwsem); list_add_tail(&shrinker->list, &shrinker_list); -#ifdef CONFIG_MEMCG - if (shrinker->flags & SHRINKER_MEMCG_AWARE) - idr_replace(&shrinker_idr, shrinker, shrinker->id); -#endif + shrinker->flags |= SHRINKER_REGISTERED; + shrinker_debugfs_add(shrinker); up_write(&shrinker_rwsem); } -int register_shrinker(struct shrinker *shrinker) +static int __register_shrinker(struct shrinker *shrinker) { - int err = prealloc_shrinker(shrinker); + int err = __prealloc_shrinker(shrinker); if (err) return err; register_shrinker_prepared(shrinker); return 0; } + +#ifdef CONFIG_SHRINKER_DEBUG +int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + va_list ap; + int err; + + va_start(ap, fmt); + shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); + va_end(ap); + if (!shrinker->name) + return -ENOMEM; + + err = __register_shrinker(shrinker); + if (err) { + kfree_const(shrinker->name); + shrinker->name = NULL; + } + return err; +} +#else +int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + return __register_shrinker(shrinker); +} +#endif EXPORT_SYMBOL(register_shrinker); /* @@ -396,18 +740,37 @@ EXPORT_SYMBOL(register_shrinker); */ void unregister_shrinker(struct shrinker *shrinker) { - if (!shrinker->nr_deferred) + if (!(shrinker->flags & SHRINKER_REGISTERED)) return; - if (shrinker->flags & SHRINKER_MEMCG_AWARE) - unregister_memcg_shrinker(shrinker); + down_write(&shrinker_rwsem); list_del(&shrinker->list); + shrinker->flags &= ~SHRINKER_REGISTERED; + if (shrinker->flags & SHRINKER_MEMCG_AWARE) + unregister_memcg_shrinker(shrinker); + shrinker_debugfs_remove(shrinker); up_write(&shrinker_rwsem); + kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; } EXPORT_SYMBOL(unregister_shrinker); +/** + * synchronize_shrinkers - Wait for all running shrinkers to complete. + * + * This is equivalent to calling unregister_shrink() and register_shrinker(), + * but atomically and with less overhead. This is useful to guarantee that all + * shrinker invocations have seen an update, before freeing memory, similar to + * rcu. + */ +void synchronize_shrinkers(void) +{ + down_write(&shrinker_rwsem); + up_write(&shrinker_rwsem); +} +EXPORT_SYMBOL(synchronize_shrinkers); + #define SHRINK_BATCH 128 static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, @@ -419,14 +782,10 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, long freeable; long nr; long new_nr; - int nid = shrinkctl->nid; long batch_size = shrinker->batch ? shrinker->batch : SHRINK_BATCH; long scanned = 0, next_deferred; - if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) - nid = 0; - freeable = shrinker->count_objects(shrinker, shrinkctl); if (freeable == 0 || freeable == SHRINK_EMPTY) return freeable; @@ -436,9 +795,8 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, * and zero it so that other concurrent shrinker invocations * don't also do this scanning work. */ - nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0); + nr = xchg_nr_deferred(shrinker, shrinkctl); - total_scan = nr; if (shrinker->seeks) { delta = freeable >> priority; delta *= 4; @@ -452,37 +810,9 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, delta = freeable / 2; } + total_scan = nr >> priority; total_scan += delta; - if (total_scan < 0) { - pr_err("shrink_slab: %pS negative objects to delete nr=%ld\n", - shrinker->scan_objects, total_scan); - total_scan = freeable; - next_deferred = nr; - } else - next_deferred = total_scan; - - /* - * We need to avoid excessive windup on filesystem shrinkers - * due to large numbers of GFP_NOFS allocations causing the - * shrinkers to return -1 all the time. This results in a large - * nr being built up so when a shrink that can do some work - * comes along it empties the entire cache due to nr >>> - * freeable. This is bad for sustaining a working set in - * memory. - * - * Hence only allow the shrinker to scan the entire cache when - * a large delta change is calculated directly. - */ - if (delta < freeable / 4) - total_scan = min(total_scan, freeable / 2); - - /* - * Avoid risking looping forever due to too large nr value: - * never try to free more than twice the estimate number of - * freeable entries. - */ - if (total_scan > freeable * 2) - total_scan = freeable * 2; + total_scan = min(total_scan, (2 * freeable)); trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, freeable, delta, total_scan, priority); @@ -521,22 +851,22 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, cond_resched(); } - if (next_deferred >= scanned) - next_deferred -= scanned; - else - next_deferred = 0; + /* + * The deferred work is increased by any new work (delta) that wasn't + * done, decreased by old deferred work that was done now. + * + * And it is capped to two times of the freeable items. + */ + next_deferred = max_t(long, (nr + delta - scanned), 0); + next_deferred = min(next_deferred, (2 * freeable)); + /* * move the unused scan count back into the shrinker in a - * manner that handles concurrent updates. If we exhausted the - * scan, there is no need to do an update. + * manner that handles concurrent updates. */ - if (next_deferred > 0) - new_nr = atomic_long_add_return(next_deferred, - &shrinker->nr_deferred[nid]); - else - new_nr = atomic_long_read(&shrinker->nr_deferred[nid]); + new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl); - trace_mm_shrink_slab_end(shrinker, nid, freed, nr, new_nr, total_scan); + trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan); return freed; } @@ -544,7 +874,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { - struct memcg_shrinker_map *map; + struct shrinker_info *info; unsigned long ret, freed = 0; int i; @@ -554,12 +884,11 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, if (!down_read_trylock(&shrinker_rwsem)) return 0; - map = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_map, - true); - if (unlikely(!map)) + info = shrinker_info_protected(memcg, nid); + if (unlikely(!info)) goto unlock; - for_each_set_bit(i, map->map, shrinker_nr_max) { + for_each_set_bit(i, info->map, shrinker_nr_max) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, @@ -568,9 +897,9 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct shrinker *shrinker; shrinker = idr_find(&shrinker_idr, i); - if (unlikely(!shrinker || shrinker == SHRINKER_REGISTERING)) { + if (unlikely(!shrinker || !(shrinker->flags & SHRINKER_REGISTERED))) { if (!shrinker) - clear_bit(i, map->map); + clear_bit(i, info->map); continue; } @@ -581,7 +910,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) { - clear_bit(i, map->map); + clear_bit(i, info->map); /* * After the shrinker reported that it had no objects to * free, but before we cleared the corresponding bit in @@ -590,7 +919,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, * case, we invoke the shrinker one more time and reset * the bit if it reports that it is not empty anymore. * The memory barrier here pairs with the barrier in - * memcg_set_shrinker_bit(): + * set_shrinker_bit(): * * list_lru_add() shrink_slab_memcg() * list_add_tail() clear_bit() @@ -602,7 +931,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, if (ret == SHRINK_EMPTY) ret = 0; else - memcg_set_shrinker_bit(memcg, nid, i); + set_shrinker_bit(memcg, nid, i); } freed += ret; @@ -676,7 +1005,7 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, freed += ret; /* * Bail out if someone want to register a new shrinker to - * prevent the regsitration from being stalled for long periods + * prevent the registration from being stalled for long periods * by parallel ongoing shrinking. */ if (rwsem_is_contended(&shrinker_rwsem)) { @@ -691,19 +1020,23 @@ out: return freed; } -void drop_slab_node(int nid) +static void drop_slab_node(int nid) { unsigned long freed; + int shift = 0; do { struct mem_cgroup *memcg = NULL; + if (fatal_signal_pending(current)) + return; + freed = 0; 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); - } while (freed > 10); + } while ((freed >> shift++) > 1); } void drop_slab(void) @@ -714,95 +1047,212 @@ void drop_slab(void) drop_slab_node(nid); } -static inline int is_page_cache_freeable(struct page *page) +static inline int is_page_cache_freeable(struct folio *folio) { /* - * A freeable page cache page is referenced only by the caller - * that isolated the page, the page cache and optional buffer - * heads at page->private. + * 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. */ - int page_cache_pins = PageTransHuge(page) && PageSwapCache(page) ? - HPAGE_PMD_NR : 1; - return page_count(page) - page_has_private(page) == 1 + page_cache_pins; -} - -static int may_write_to_inode(struct inode *inode) -{ - if (current->flags & PF_SWAPWRITE) - return 1; - if (!inode_write_congested(inode)) - return 1; - if (inode_to_bdi(inode) == current->backing_dev_info) - return 1; - return 0; + return folio_ref_count(folio) - folio_test_private(folio) == + 1 + folio_nr_pages(folio); } /* - * We detected a synchronous write error writing a page out. Probably + * 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 page and once - * that page is locked, the mapping is pinned. + * 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 lock_page() here because we know the caller has + * 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 page *page, int error) + struct folio *folio, int error) { - lock_page(page); - if (page_mapping(page) == mapping) + folio_lock(folio); + if (folio_mapping(folio) == mapping) mapping_set_error(mapping, error); - unlock_page(page); + 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 IO 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_IO_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 page out, page is locked */ + /* failed to write folio out, folio is locked */ PAGE_KEEP, - /* move page to the active list, page is locked */ + /* move folio to the active list, folio is locked */ PAGE_ACTIVATE, - /* page has been sent to the disk successfully, page is unlocked */ + /* folio has been sent to the disk successfully, folio is unlocked */ PAGE_SUCCESS, - /* page is clean and locked */ + /* folio is clean and locked */ PAGE_CLEAN, } pageout_t; /* - * pageout is called by shrink_page_list() for each dirty page. + * pageout is called by shrink_folio_list() for each dirty folio. * Calls ->writepage(). */ -static pageout_t pageout(struct page *page, struct address_space *mapping) +static pageout_t pageout(struct folio *folio, struct address_space *mapping, + struct swap_iocb **plug) { /* - * If the page is dirty, only perform writeback if that write + * 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 page's queue, we can perform writeback even if that + * this folio's queue, we can perform writeback even if that * will block. * - * If the page is swapcache, write it back even if that would + * 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(page)) + if (!is_page_cache_freeable(folio)) return PAGE_KEEP; if (!mapping) { /* - * Some data journaling orphaned pages can have - * page->mapping == NULL while being dirty with clean buffers. + * Some data journaling orphaned folios can have + * folio->mapping == NULL while being dirty with clean buffers. */ - if (page_has_private(page)) { - if (try_to_free_buffers(page)) { - ClearPageDirty(page); - pr_info("%s: orphaned page\n", __func__); + 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; } } @@ -810,10 +1260,8 @@ static pageout_t pageout(struct page *page, struct address_space *mapping) } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; - if (!may_write_to_inode(mapping->host)) - return PAGE_KEEP; - if (clear_page_dirty_for_io(page)) { + if (folio_clear_dirty_for_io(folio)) { int res; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, @@ -821,23 +1269,24 @@ static pageout_t pageout(struct page *page, struct address_space *mapping) .range_start = 0, .range_end = LLONG_MAX, .for_reclaim = 1, + .swap_plug = plug, }; - SetPageReclaim(page); - res = mapping->a_ops->writepage(page, &wbc); + folio_set_reclaim(folio); + res = mapping->a_ops->writepage(&folio->page, &wbc); if (res < 0) - handle_write_error(mapping, page, res); + handle_write_error(mapping, folio, res); if (res == AOP_WRITEPAGE_ACTIVATE) { - ClearPageReclaim(page); + folio_clear_reclaim(folio); return PAGE_ACTIVATE; } - if (!PageWriteback(page)) { + if (!folio_test_writeback(folio)) { /* synchronous write or broken a_ops? */ - ClearPageReclaim(page); + folio_clear_reclaim(folio); } - trace_mm_vmscan_writepage(page); - inc_node_page_state(page, NR_VMSCAN_WRITE); + trace_mm_vmscan_write_folio(folio); + node_stat_add_folio(folio, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } @@ -845,334 +1294,446 @@ static pageout_t pageout(struct page *page, struct address_space *mapping) } /* - * Same as remove_mapping, but if the page is removed from the mapping, it + * 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 page *page, +static int __remove_mapping(struct address_space *mapping, struct folio *folio, bool reclaimed, struct mem_cgroup *target_memcg) { - unsigned long flags; int refcount; + void *shadow = NULL; - BUG_ON(!PageLocked(page)); - BUG_ON(mapping != page_mapping(page)); + BUG_ON(!folio_test_locked(folio)); + BUG_ON(mapping != folio_mapping(folio)); - xa_lock_irqsave(&mapping->i_pages, flags); + if (!folio_test_swapcache(folio)) + spin_lock(&mapping->host->i_lock); + xa_lock_irq(&mapping->i_pages); /* - * The non racy check for a busy page. + * The non racy check for a busy folio. * * Must be careful with the order of the tests. When someone has - * a ref to the page, it may be possible that they dirty it then - * drop the reference. So if PageDirty is tested before page_count - * here, then the following race may occur: + * 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); - * !PageDirty(page) [good] - * SetPageDirty(page); - * put_page(page); - * !page_count(page) [good, discard it] + * !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 page->flags - * load is not satisfied before that of page->_refcount. + * escape unnoticed. The smp_rmb is needed to ensure the folio->flags + * load is not satisfied before that of folio->_refcount. * - * Note that if SetPageDirty is always performed via set_page_dirty, + * 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 + compound_nr(page); - if (!page_ref_freeze(page, refcount)) + refcount = 1 + folio_nr_pages(folio); + if (!folio_ref_freeze(folio, refcount)) goto cannot_free; - /* note: atomic_cmpxchg in page_ref_freeze provides the smp_rmb */ - if (unlikely(PageDirty(page))) { - page_ref_unfreeze(page, refcount); + /* 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 (PageSwapCache(page)) { - swp_entry_t swap = { .val = page_private(page) }; - mem_cgroup_swapout(page, swap); - __delete_from_swap_cache(page, swap); - xa_unlock_irqrestore(&mapping->i_pages, flags); - put_swap_page(page, swap); + if (folio_test_swapcache(folio)) { + swp_entry_t swap = folio_swap_entry(folio); + + /* 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_folio(folio, swap); } else { - void (*freepage)(struct page *); - void *shadow = NULL; + void (*free_folio)(struct folio *); - freepage = mapping->a_ops->freepage; + 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 optizimation, + * 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 pages found in these are zero pages + * 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 && page_is_file_cache(page) && + if (reclaimed && folio_is_file_lru(folio) && !mapping_exiting(mapping) && !dax_mapping(mapping)) - shadow = workingset_eviction(page, target_memcg); - __delete_from_page_cache(page, shadow); - xa_unlock_irqrestore(&mapping->i_pages, flags); - - if (freepage != NULL) - freepage(page); + 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_irqrestore(&mapping->i_pages, flags); + xa_unlock_irq(&mapping->i_pages); + if (!folio_test_swapcache(folio)) + spin_unlock(&mapping->host->i_lock); return 0; } -/* - * Attempt to detach a locked page from its ->mapping. If it is dirty or if - * someone else has a ref on the page, abort and return 0. If it was - * successfully detached, return 1. Assumes the caller has a single ref on - * this page. +/** + * 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. */ -int remove_mapping(struct address_space *mapping, struct page *page) +long remove_mapping(struct address_space *mapping, struct folio *folio) { - if (__remove_mapping(mapping, page, false, NULL)) { + if (__remove_mapping(mapping, folio, false, NULL)) { /* - * Unfreezing the refcount with 1 rather than 2 effectively + * Unfreezing the refcount with 1 effectively * drops the pagecache ref for us without requiring another * atomic operation. */ - page_ref_unfreeze(page, 1); - return 1; + folio_ref_unfreeze(folio, 1); + return folio_nr_pages(folio); } return 0; } /** - * putback_lru_page - put previously isolated page onto appropriate LRU list - * @page: page to be put back to appropriate lru list + * folio_putback_lru - Put previously isolated folio onto appropriate LRU list. + * @folio: Folio to be returned to an LRU list. * - * Add previously isolated @page to appropriate LRU list. - * Page may still be unevictable for other reasons. + * Add previously isolated @folio to appropriate LRU list. + * The folio may still be unevictable for other reasons. * - * lru_lock must not be held, interrupts must be enabled. + * Context: lru_lock must not be held, interrupts must be enabled. */ -void putback_lru_page(struct page *page) +void folio_putback_lru(struct folio *folio) { - lru_cache_add(page); - put_page(page); /* drop ref from isolate */ + folio_add_lru(folio); + folio_put(folio); /* drop ref from isolate */ } -enum page_references { - PAGEREF_RECLAIM, - PAGEREF_RECLAIM_CLEAN, - PAGEREF_KEEP, - PAGEREF_ACTIVATE, +enum folio_references { + FOLIOREF_RECLAIM, + FOLIOREF_RECLAIM_CLEAN, + FOLIOREF_KEEP, + FOLIOREF_ACTIVATE, }; -static enum page_references page_check_references(struct page *page, +static enum folio_references folio_check_references(struct folio *folio, struct scan_control *sc) { - int referenced_ptes, referenced_page; + int referenced_ptes, referenced_folio; unsigned long vm_flags; - referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup, - &vm_flags); - referenced_page = TestClearPageReferenced(page); + referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup, + &vm_flags); + referenced_folio = folio_test_clear_referenced(folio); /* - * Mlock lost the isolation race with us. Let try_to_unmap() - * move the page to the unevictable list. + * 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 PAGEREF_RECLAIM; + return FOLIOREF_ACTIVATE; + + /* rmap lock contention: rotate */ + if (referenced_ptes == -1) + return FOLIOREF_KEEP; if (referenced_ptes) { - if (PageSwapBacked(page)) - return PAGEREF_ACTIVATE; /* - * All mapped pages start out with page table + * All mapped folios start out with page table * references from the instantiating fault, so we need - * to look twice if a mapped file page is used more + * 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 pages as well - * so that recently deactivated but used pages are + * Note: the mark is set for activated folios as well + * so that recently deactivated but used folios are * quickly recovered. */ - SetPageReferenced(page); + folio_set_referenced(folio); - if (referenced_page || referenced_ptes > 1) - return PAGEREF_ACTIVATE; + if (referenced_folio || referenced_ptes > 1) + return FOLIOREF_ACTIVATE; /* - * Activate file-backed executable pages after first usage. + * Activate file-backed executable folios after first usage. */ - if (vm_flags & VM_EXEC) - return PAGEREF_ACTIVATE; + if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) + return FOLIOREF_ACTIVATE; - return PAGEREF_KEEP; + return FOLIOREF_KEEP; } - /* Reclaim if clean, defer dirty pages to writeback */ - if (referenced_page && !PageSwapBacked(page)) - return PAGEREF_RECLAIM_CLEAN; + /* Reclaim if clean, defer dirty folios to writeback */ + if (referenced_folio && folio_is_file_lru(folio)) + return FOLIOREF_RECLAIM_CLEAN; - return PAGEREF_RECLAIM; + return FOLIOREF_RECLAIM; } -/* Check if a page is dirty or under writeback */ -static void page_check_dirty_writeback(struct page *page, +/* 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 pages are not handled by flushers and must be written - * from reclaim context. Do not stall reclaim based on them + * 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 (!page_is_file_cache(page) || - (PageAnon(page) && !PageSwapBacked(page))) { + if (!folio_is_file_lru(folio) || + (folio_test_anon(folio) && !folio_test_swapbacked(folio))) { *dirty = false; *writeback = false; return; } - /* By default assume that the page flags are accurate */ - *dirty = PageDirty(page); - *writeback = PageWriteback(page); + /* 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 (!page_has_private(page)) + if (!folio_test_private(folio)) return; - mapping = page_mapping(page); + mapping = folio_mapping(folio); if (mapping && mapping->a_ops->is_dirty_writeback) - mapping->a_ops->is_dirty_writeback(page, dirty, writeback); + mapping->a_ops->is_dirty_writeback(folio, dirty, writeback); +} + +static struct page *alloc_demote_page(struct page *page, unsigned long private) +{ + struct page *target_page; + 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; + target_page = alloc_migration_target(page, (unsigned long)mtc); + if (target_page) + return target_page; + + mtc->gfp_mask &= ~__GFP_THISNODE; + mtc->nmask = allowed_mask; + + return alloc_migration_target(page, (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 + }; + + 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_page, NULL, + (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION, + &nr_succeeded); + + if (current_is_kswapd()) + __count_vm_events(PGDEMOTE_KSWAPD, nr_succeeded); + else + __count_vm_events(PGDEMOTE_DIRECT, 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_page_list() returns the number of reclaimed pages + * shrink_folio_list() returns the number of reclaimed pages */ -static unsigned long shrink_page_list(struct list_head *page_list, - struct pglist_data *pgdat, - struct scan_control *sc, - enum ttu_flags ttu_flags, - struct reclaim_stat *stat, - bool ignore_references) -{ - LIST_HEAD(ret_pages); - LIST_HEAD(free_pages); - unsigned nr_reclaimed = 0; - unsigned pgactivate = 0; +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) +{ + LIST_HEAD(ret_folios); + LIST_HEAD(free_folios); + LIST_HEAD(demote_folios); + unsigned int nr_reclaimed = 0; + unsigned int pgactivate = 0; + bool do_demote_pass; + struct swap_iocb *plug = NULL; memset(stat, 0, sizeof(*stat)); cond_resched(); + do_demote_pass = can_demote(pgdat->node_id, sc); - while (!list_empty(page_list)) { +retry: + while (!list_empty(folio_list)) { struct address_space *mapping; - struct page *page; - int may_enter_fs; - enum page_references references = PAGEREF_RECLAIM; + struct folio *folio; + enum folio_references references = FOLIOREF_RECLAIM; bool dirty, writeback; unsigned int nr_pages; cond_resched(); - page = lru_to_page(page_list); - list_del(&page->lru); + folio = lru_to_folio(folio_list); + list_del(&folio->lru); - if (!trylock_page(page)) + if (!folio_trylock(folio)) goto keep; - VM_BUG_ON_PAGE(PageActive(page), page); + VM_BUG_ON_FOLIO(folio_test_active(folio), folio); - nr_pages = compound_nr(page); + nr_pages = folio_nr_pages(folio); - /* Account the number of base pages even though THP */ + /* Account the number of base pages */ sc->nr_scanned += nr_pages; - if (unlikely(!page_evictable(page))) + if (unlikely(!folio_evictable(folio))) goto activate_locked; - if (!sc->may_unmap && page_mapped(page)) + if (!sc->may_unmap && folio_mapped(folio)) goto keep_locked; - may_enter_fs = (sc->gfp_mask & __GFP_FS) || - (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO)); + /* 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 which affects wait_iff_congested. kswapd - * will stall and start writing pages if the tail of the LRU - * is all dirty unqueued pages. + * reclaim_congested. kswapd will stall and start writing + * folios if the tail of the LRU is all dirty unqueued folios. */ - page_check_dirty_writeback(page, &dirty, &writeback); + folio_check_dirty_writeback(folio, &dirty, &writeback); if (dirty || writeback) - stat->nr_dirty++; + stat->nr_dirty += nr_pages; if (dirty && !writeback) - stat->nr_unqueued_dirty++; + stat->nr_unqueued_dirty += nr_pages; /* - * Treat this page as congested if the underlying BDI is or if - * pages are cycling through the LRU so quickly that the - * pages marked for immediate reclaim are making it to the - * end of the LRU a second time. + * 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. */ - mapping = page_mapping(page); - if (((dirty || writeback) && mapping && - inode_write_congested(mapping->host)) || - (writeback && PageReclaim(page))) - stat->nr_congested++; + if (writeback && folio_test_reclaim(folio)) + stat->nr_congested += nr_pages; /* - * If a page at the tail of the LRU is under writeback, there + * 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 pages - * under writeback and this page is both under writeback and - * PageReclaim then it indicates that pages are being queued - * for IO but are being recycled through the LRU before the - * IO can complete. Waiting on the page itself risks an - * indefinite stall if it is impossible to writeback the - * page due to IO error or disconnected storage so instead - * note that the LRU is being scanned too quickly and the - * caller can stall after page list has been processed. + * 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 page that is + * 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 page for immediate + * 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 IO yet. And the loop driver might - * enter reclaim, and deadlock if it waits on a page for + * 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 page that is already marked - * PageReclaim. memcg does not have any dirty pages + * 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 - * pages are in writeback and there is nothing else to + * 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 pages to get them out of - * the way while we continue scanning for clean pages on the + * 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. @@ -1180,268 +1741,298 @@ static unsigned long shrink_page_list(struct list_head *page_list, * memory pressure on the cache working set any longer than it * takes to write them to disk. */ - if (PageWriteback(page)) { + if (folio_test_writeback(folio)) { /* Case 1 above */ if (current_is_kswapd() && - PageReclaim(page) && + folio_test_reclaim(folio) && test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { - stat->nr_immediate++; + stat->nr_immediate += nr_pages; goto activate_locked; /* Case 2 above */ } else if (writeback_throttling_sane(sc) || - !PageReclaim(page) || !may_enter_fs) { + !folio_test_reclaim(folio) || + !may_enter_fs(folio, sc->gfp_mask)) { /* - * This is slightly racy - end_page_writeback() - * might have just cleared PageReclaim, then - * setting PageReclaim here end up interpreted - * as PageReadahead - but that does not matter - * enough to care. What we do want is for this - * page to have PageReclaim set next time memcg - * reclaim reaches the tests above, so it will - * then wait_on_page_writeback() to avoid OOM; - * and it's also appropriate in global reclaim. + * 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. */ - SetPageReclaim(page); - stat->nr_writeback++; + folio_set_reclaim(folio); + stat->nr_writeback += nr_pages; goto activate_locked; /* Case 3 above */ } else { - unlock_page(page); - wait_on_page_writeback(page); - /* then go back and try same page again */ - list_add_tail(&page->lru, page_list); + 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 = page_check_references(page, sc); + references = folio_check_references(folio, sc); switch (references) { - case PAGEREF_ACTIVATE: + case FOLIOREF_ACTIVATE: goto activate_locked; - case PAGEREF_KEEP: + case FOLIOREF_KEEP: stat->nr_ref_keep += nr_pages; goto keep_locked; - case PAGEREF_RECLAIM: - case PAGEREF_RECLAIM_CLEAN: - ; /* try to reclaim the page below */ + 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 page could be freed directly + * Lazyfree folio could be freed directly */ - if (PageAnon(page) && PageSwapBacked(page)) { - if (!PageSwapCache(page)) { + if (folio_test_anon(folio) && folio_test_swapbacked(folio)) { + if (!folio_test_swapcache(folio)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; - if (PageTransHuge(page)) { - /* cannot split THP, skip it */ - if (!can_split_huge_page(page, NULL)) + 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 pages without a PMD map right + * Split folios without a PMD map right * away. Chances are some or all of the * tail pages can be freed without IO. */ - if (!compound_mapcount(page) && - split_huge_page_to_list(page, - page_list)) + if (!folio_entire_mapcount(folio) && + split_folio_to_list(folio, + folio_list)) goto activate_locked; } - if (!add_to_swap(page)) { - if (!PageTransHuge(page)) + if (!add_to_swap(folio)) { + if (!folio_test_large(folio)) goto activate_locked_split; /* Fallback to swap normal pages */ - if (split_huge_page_to_list(page, - page_list)) + if (split_folio_to_list(folio, + folio_list)) goto activate_locked; #ifdef CONFIG_TRANSPARENT_HUGEPAGE count_vm_event(THP_SWPOUT_FALLBACK); #endif - if (!add_to_swap(page)) + if (!add_to_swap(folio)) goto activate_locked_split; } - - may_enter_fs = 1; - - /* Adding to swap updated mapping */ - mapping = page_mapping(page); } - } else if (unlikely(PageTransHuge(page))) { - /* Split file THP */ - if (split_huge_page_to_list(page, page_list)) + } else if (folio_test_swapbacked(folio) && + folio_test_large(folio)) { + /* Split shmem folio */ + if (split_folio_to_list(folio, folio_list)) goto keep_locked; } /* - * THP may get split above, need minus tail pages and update - * nr_pages to avoid accounting tail pages twice. - * - * The tail pages that are added into swap cache successfully - * reach here. + * 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) && !PageTransHuge(page)) { + if ((nr_pages > 1) && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } /* - * The page is mapped into the page tables of one or more + * The folio is mapped into the page tables of one or more * processes. Try to unmap it here. */ - if (page_mapped(page)) { - enum ttu_flags flags = ttu_flags | TTU_BATCH_FLUSH; + if (folio_mapped(folio)) { + enum ttu_flags flags = TTU_BATCH_FLUSH; + bool was_swapbacked = folio_test_swapbacked(folio); - if (unlikely(PageTransHuge(page))) + if (folio_test_pmd_mappable(folio)) flags |= TTU_SPLIT_HUGE_PMD; - if (!try_to_unmap(page, flags)) { + + 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; } } - if (PageDirty(page)) { + mapping = folio_mapping(folio); + if (folio_test_dirty(folio)) { /* - * Only kswapd can writeback filesystem pages + * Only kswapd can writeback filesystem folios * to avoid risk of stack overflow. But avoid - * injecting inefficient single-page IO into + * injecting inefficient single-folio I/O into * flusher writeback as much as possible: only - * write pages when we've encountered many - * dirty pages, and when we've already scanned - * the rest of the LRU for clean pages and see - * the same dirty pages again (PageReclaim). + * 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 (page_is_file_cache(page) && - (!current_is_kswapd() || !PageReclaim(page) || + 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 principal to deactivate_page() - * except we already have the page isolated + * Similar in principle to deactivate_page() + * except we already have the folio isolated * and know it's dirty */ - inc_node_page_state(page, NR_VMSCAN_IMMEDIATE); - SetPageReclaim(page); + node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE, + nr_pages); + folio_set_reclaim(folio); goto activate_locked; } - if (references == PAGEREF_RECLAIM_CLEAN) + if (references == FOLIOREF_RECLAIM_CLEAN) goto keep_locked; - if (!may_enter_fs) + if (!may_enter_fs(folio, sc->gfp_mask)) goto keep_locked; if (!sc->may_writepage) goto keep_locked; /* - * Page is dirty. Flush the TLB if a writable entry - * potentially exists to avoid CPU writes after IO + * 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(page, mapping)) { + switch (pageout(folio, mapping, &plug)) { case PAGE_KEEP: goto keep_locked; case PAGE_ACTIVATE: goto activate_locked; case PAGE_SUCCESS: - if (PageWriteback(page)) + stat->nr_pageout += nr_pages; + + if (folio_test_writeback(folio)) goto keep; - if (PageDirty(page)) + if (folio_test_dirty(folio)) goto keep; /* * A synchronous write - probably a ramdisk. Go - * ahead and try to reclaim the page. + * ahead and try to reclaim the folio. */ - if (!trylock_page(page)) + if (!folio_trylock(folio)) goto keep; - if (PageDirty(page) || PageWriteback(page)) + if (folio_test_dirty(folio) || + folio_test_writeback(folio)) goto keep_locked; - mapping = page_mapping(page); + mapping = folio_mapping(folio); + fallthrough; case PAGE_CLEAN: - ; /* try to free the page below */ + ; /* try to free the folio below */ } } /* - * If the page has buffers, try to free the buffer mappings - * associated with this page. If we succeed we try to free - * the page as well. + * 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 page is PageDirty(). - * try_to_release_page() does not perform I/O, but it is - * possible for a page to have PageDirty 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. - * try_to_release_page() will discover that cleanness and will - * drop the buffers and mark the page clean - it can be freed. + * 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, pages can have buffers and no ->mapping. These are - * the pages which were not successfully invalidated in - * truncate_complete_page(). We try to drop those buffers here - * and if that worked, and the page is no longer mapped into - * process address space (page_count == 1) it can be freed. - * Otherwise, leave the page on the LRU so it is swappable. + * 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 (page_has_private(page)) { - if (!try_to_release_page(page, sc->gfp_mask)) + if (folio_has_private(folio)) { + if (!filemap_release_folio(folio, sc->gfp_mask)) goto activate_locked; - if (!mapping && page_count(page) == 1) { - unlock_page(page); - if (put_page_testzero(page)) + 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 page shortly, so we may + * this folio shortly, so we may * increment nr_reclaimed here (and * leave it off the LRU). */ - nr_reclaimed++; + nr_reclaimed += nr_pages; continue; } } } - if (PageAnon(page) && !PageSwapBacked(page)) { + if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) { /* follow __remove_mapping for reference */ - if (!page_ref_freeze(page, 1)) + if (!folio_ref_freeze(folio, 1)) goto keep_locked; - if (PageDirty(page)) { - page_ref_unfreeze(page, 1); - goto keep_locked; - } - - count_vm_event(PGLAZYFREED); - count_memcg_page_event(page, PGLAZYFREED); - } else if (!mapping || !__remove_mapping(mapping, page, true, + /* + * 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; - unlock_page(page); + folio_unlock(folio); free_it: /* - * THP may get swapped out in a whole, need account - * all base pages. + * Folio may get swapped out as a whole, need to account + * all pages in it. */ nr_reclaimed += nr_pages; /* - * Is there need to periodically free_page_list? It would + * Is there need to periodically free_folio_list? It would * appear not as the counts should be low */ - if (unlikely(PageTransHuge(page))) - (*get_compound_page_dtor(page))(page); + if (unlikely(folio_test_large(folio))) + destroy_large_folio(folio); else - list_add(&page->lru, &free_pages); + list_add(&folio->lru, &free_folios); continue; activate_locked_split: @@ -1455,144 +2046,101 @@ activate_locked_split: } activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ - if (PageSwapCache(page) && (mem_cgroup_swap_full(page) || - PageMlocked(page))) - try_to_free_swap(page); - VM_BUG_ON_PAGE(PageActive(page), page); - if (!PageMlocked(page)) { - int type = page_is_file_cache(page); - SetPageActive(page); + 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_page_event(page, PGACTIVATE); + count_memcg_folio_events(folio, PGACTIVATE, nr_pages); } keep_locked: - unlock_page(page); + folio_unlock(folio); keep: - list_add(&page->lru, &ret_pages); - VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); + 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 for retry: */ + list_splice_init(&demote_folios, folio_list); + do_demote_pass = false; + goto retry; } pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; - mem_cgroup_uncharge_list(&free_pages); + mem_cgroup_uncharge_list(&free_folios); try_to_unmap_flush(); - free_unref_page_list(&free_pages); + free_unref_page_list(&free_folios); - list_splice(&ret_pages, page_list); + list_splice(&ret_folios, folio_list); count_vm_events(PGACTIVATE, pgactivate); + if (plug) + swap_write_unplug(plug); return nr_reclaimed; } -unsigned long reclaim_clean_pages_from_list(struct zone *zone, - struct list_head *page_list) +unsigned int reclaim_clean_pages_from_list(struct zone *zone, + struct list_head *folio_list) { struct scan_control sc = { .gfp_mask = GFP_KERNEL, - .priority = DEF_PRIORITY, .may_unmap = 1, }; - struct reclaim_stat dummy_stat; - unsigned long ret; - struct page *page, *next; - LIST_HEAD(clean_pages); - - list_for_each_entry_safe(page, next, page_list, lru) { - if (page_is_file_cache(page) && !PageDirty(page) && - !__PageMovable(page) && !PageUnevictable(page)) { - ClearPageActive(page); - list_move(&page->lru, &clean_pages); + 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); } } - ret = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, - TTU_IGNORE_ACCESS, &dummy_stat, true); - list_splice(&clean_pages, page_list); - mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -ret); - return ret; -} - -/* - * Attempt to remove the specified page from its LRU. Only take this page - * if it is of the appropriate PageActive status. Pages which are being - * freed elsewhere are also ignored. - * - * page: page to consider - * mode: one of the LRU isolation modes defined above - * - * returns 0 on success, -ve errno on failure. - */ -int __isolate_lru_page(struct page *page, isolate_mode_t mode) -{ - int ret = -EINVAL; - - /* Only take pages on the LRU. */ - if (!PageLRU(page)) - return ret; - - /* Compaction should not handle unevictable pages but CMA can do so */ - if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE)) - return ret; - - ret = -EBUSY; - /* - * To minimise LRU disruption, the caller can indicate that it only - * wants to isolate pages it will be able to operate on without - * blocking - clean pages for the most part. - * - * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages - * that it is possible to migrate without blocking + * 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. */ - if (mode & ISOLATE_ASYNC_MIGRATE) { - /* All the caller can do on PageWriteback is block */ - if (PageWriteback(page)) - return ret; - - if (PageDirty(page)) { - struct address_space *mapping; - bool migrate_dirty; - - /* - * Only pages without mappings or that have a - * ->migratepage callback are possible to migrate - * without blocking. However, we can be racing with - * truncation so it's necessary to lock the page - * to stabilise the mapping as truncation holds - * the page lock until after the page is removed - * from the page cache. - */ - if (!trylock_page(page)) - return ret; - - mapping = page_mapping(page); - migrate_dirty = !mapping || mapping->a_ops->migratepage; - unlock_page(page); - if (!migrate_dirty) - return ret; - } - } - - if ((mode & ISOLATE_UNMAPPED) && page_mapped(page)) - return ret; - - if (likely(get_page_unless_zero(page))) { - /* - * Be careful not to clear PageLRU until after we're - * sure the page is not being freed elsewhere -- the - * page release code relies on it. - */ - ClearPageLRU(page); - ret = 0; - } + noreclaim_flag = memalloc_noreclaim_save(); + nr_reclaimed = shrink_folio_list(&clean_folios, zone->zone_pgdat, &sc, + &stat, true); + memalloc_noreclaim_restore(noreclaim_flag); - return ret; + 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 santity check. + * 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) @@ -1603,35 +2151,33 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec, if (!nr_zone_taken[zid]) continue; - __update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); -#ifdef CONFIG_MEMCG - mem_cgroup_update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); -#endif + update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); } } -/** - * pgdat->lru_lock is heavily contended. Some of the functions that +/* + * 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). * - * Appropriate locks must be held before calling this function. + * 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 - * @mode: One of the LRU isolation modes * @lru: LRU list id for isolating * * returns how many pages were moved onto *@dst. */ -static unsigned long isolate_lru_pages(unsigned long nr_to_scan, +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) @@ -1642,67 +2188,72 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; unsigned long skipped = 0; unsigned long scan, total_scan, nr_pages; - LIST_HEAD(pages_skipped); - isolate_mode_t mode = (sc->may_unmap ? 0 : ISOLATE_UNMAPPED); + LIST_HEAD(folios_skipped); total_scan = 0; scan = 0; while (scan < nr_to_scan && !list_empty(src)) { - struct page *page; + struct list_head *move_to = src; + struct folio *folio; - page = lru_to_page(src); - prefetchw_prev_lru_page(page, src, flags); + folio = lru_to_folio(src); + prefetchw_prev_lru_folio(folio, src, flags); - VM_BUG_ON_PAGE(!PageLRU(page), page); - - nr_pages = compound_nr(page); + nr_pages = folio_nr_pages(folio); total_scan += nr_pages; - if (page_zonenum(page) > sc->reclaim_idx) { - list_move(&page->lru, &pages_skipped); - nr_skipped[page_zonenum(page)] += nr_pages; - continue; + if (folio_zonenum(folio) > sc->reclaim_idx) { + nr_skipped[folio_zonenum(folio)] += nr_pages; + move_to = &folios_skipped; + goto move; } /* - * Do not count skipped pages because that makes the function - * return with no isolated pages if the LRU mostly contains - * ineligible pages. This causes the VM to not reclaim any - * pages, triggering a premature OOM. - * - * Account all tail pages of THP. This would not cause - * premature OOM since __isolate_lru_page() returns -EBUSY - * only when the page is being freed somewhere else. + * 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; - switch (__isolate_lru_page(page, mode)) { - case 0: - nr_taken += nr_pages; - nr_zone_taken[page_zonenum(page)] += nr_pages; - list_move(&page->lru, dst); - break; - case -EBUSY: - /* else it is being freed elsewhere */ - list_move(&page->lru, src); - continue; + if (!folio_test_lru(folio)) + goto move; + if (!sc->may_unmap && folio_mapped(folio)) + goto move; - default: - BUG(); + /* + * 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 pages to the start of the LRU list. Note that + * 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 pages to skip and put the - * system at risk of premature OOM. + * scanning would soon rescan the same folios to skip and waste lots + * of cpu cycles. */ - if (!list_empty(&pages_skipped)) { + if (!list_empty(&folios_skipped)) { int zid; - list_splice(&pages_skipped, src); + list_splice(&folios_skipped, src); for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_skipped[zid]) continue; @@ -1713,59 +2264,51 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, } *nr_scanned = total_scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, - total_scan, skipped, nr_taken, mode, lru); + total_scan, skipped, nr_taken, + sc->may_unmap ? 0 : ISOLATE_UNMAPPED, lru); update_lru_sizes(lruvec, lru, nr_zone_taken); return nr_taken; } /** - * isolate_lru_page - tries to isolate a page from its LRU list - * @page: page to isolate from its LRU list + * folio_isolate_lru() - Try to isolate a folio from its LRU list. + * @folio: Folio to isolate from its LRU list. * - * Isolates a @page from an LRU list, clears PageLRU and adjusts the - * vmstat statistic corresponding to whatever LRU list the page was on. + * Isolate a @folio from an LRU list and adjust the vmstat statistic + * corresponding to whatever LRU list the folio was on. * - * Returns 0 if the page was removed from an LRU list. - * Returns -EBUSY if the page was not on an LRU list. - * - * The returned page will have PageLRU() cleared. If it was found on - * the active list, it will have PageActive set. If it was found on - * the unevictable list, it will have the PageUnevictable bit set. That flag + * 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. * - * The vmstat statistic corresponding to the list on which the page was - * found will be decremented. - * - * Restrictions: + * Context: * - * (1) Must be called with an elevated refcount on the page. This is a - * fundamentnal difference from isolate_lru_pages (which is called + * (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. + * (2) The lru_lock must not be held. + * (3) Interrupts must be enabled. + * + * Return: 0 if the folio was removed from an LRU list. + * -EBUSY if the folio was not on an LRU list. */ -int isolate_lru_page(struct page *page) +int folio_isolate_lru(struct folio *folio) { int ret = -EBUSY; - VM_BUG_ON_PAGE(!page_count(page), page); - WARN_RATELIMIT(PageTail(page), "trying to isolate tail page"); + VM_BUG_ON_FOLIO(!folio_ref_count(folio), folio); - if (PageLRU(page)) { - pg_data_t *pgdat = page_pgdat(page); + if (folio_test_clear_lru(folio)) { struct lruvec *lruvec; - spin_lock_irq(&pgdat->lru_lock); - lruvec = mem_cgroup_page_lruvec(page, pgdat); - if (PageLRU(page)) { - int lru = page_lru(page); - get_page(page); - ClearPageLRU(page); - del_page_from_lru_list(page, lruvec, lru); - ret = 0; - } - spin_unlock_irq(&pgdat->lru_lock); + folio_get(folio); + lruvec = folio_lruvec_lock_irq(folio); + lruvec_del_folio(lruvec, folio); + unlock_page_lruvec_irq(lruvec); + ret = 0; } + return ret; } @@ -1780,6 +2323,7 @@ static int 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 0; @@ -1803,111 +2347,111 @@ static int too_many_isolated(struct pglist_data *pgdat, int file, if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) inactive >>= 3; - return isolated > inactive; + too_many = isolated > inactive; + + /* Wake up tasks throttled due to too_many_isolated. */ + if (!too_many) + wake_throttle_isolated(pgdat); + + return too_many; } /* - * This moves pages from @list to corresponding LRU list. - * - * We move them the other way if the page is referenced by one or more - * processes, from rmap. - * - * If the pages are mostly unmapped, the processing is fast and it is - * appropriate to hold zone_lru_lock across the whole operation. But if - * the pages are mapped, the processing is slow (page_referenced()) so we - * should drop zone_lru_lock around each page. It's impossible to balance - * this, so instead we remove the pages from the LRU while processing them. - * It is safe to rely on PG_active against the non-LRU pages in here because - * nobody will play with that bit on a non-LRU page. - * - * The downside is that we have to touch page->_refcount against each page. - * But we had to alter page->flags anyway. + * move_folios_to_lru() moves folios from private @list to appropriate LRU list. + * On return, @list is reused as a list of folios to be freed by the caller. * * Returns the number of pages moved to the given lruvec. */ - -static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, - struct list_head *list) +static unsigned int move_folios_to_lru(struct lruvec *lruvec, + struct list_head *list) { - struct pglist_data *pgdat = lruvec_pgdat(lruvec); int nr_pages, nr_moved = 0; - LIST_HEAD(pages_to_free); - struct page *page; - enum lru_list lru; + LIST_HEAD(folios_to_free); while (!list_empty(list)) { - page = lru_to_page(list); - VM_BUG_ON_PAGE(PageLRU(page), page); - if (unlikely(!page_evictable(page))) { - list_del(&page->lru); - spin_unlock_irq(&pgdat->lru_lock); - putback_lru_page(page); - spin_lock_irq(&pgdat->lru_lock); + 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; } - lruvec = mem_cgroup_page_lruvec(page, pgdat); - SetPageLRU(page); - lru = page_lru(page); - - nr_pages = hpage_nr_pages(page); - update_lru_size(lruvec, lru, page_zonenum(page), nr_pages); - list_move(&page->lru, &lruvec->lists[lru]); + /* + * 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 (put_page_testzero(page)) { - __ClearPageLRU(page); - __ClearPageActive(page); - del_page_from_lru_list(page, lruvec, lru); + if (unlikely(folio_put_testzero(folio))) { + __folio_clear_lru_flags(folio); - if (unlikely(PageCompound(page))) { - spin_unlock_irq(&pgdat->lru_lock); - (*get_compound_page_dtor(page))(page); - spin_lock_irq(&pgdat->lru_lock); + if (unlikely(folio_test_large(folio))) { + spin_unlock_irq(&lruvec->lru_lock); + destroy_large_folio(folio); + spin_lock_irq(&lruvec->lru_lock); } else - list_add(&page->lru, &pages_to_free); - } else { - nr_moved += nr_pages; + list_add(&folio->lru, &folios_to_free); + + 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); } /* * To save our caller's stack, now use input list for pages to free. */ - list_splice(&pages_to_free, list); + list_splice(&folios_to_free, list); 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_LESS_THROTTLE. - * In that case we should only throttle if the backing device it is - * writing to is congested. In other cases it is safe to throttle. + * 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_LESS_THROTTLE) || - current->backing_dev_info == NULL || - bdi_write_congested(current->backing_dev_info); + return !(current->flags & PF_LOCAL_THROTTLE); } /* * shrink_inactive_list() is a helper for shrink_node(). It returns the number * of reclaimed pages */ -static noinline_for_stack unsigned long -shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, - struct scan_control *sc, enum lru_list lru) +static unsigned long shrink_inactive_list(unsigned long nr_to_scan, + struct lruvec *lruvec, struct scan_control *sc, + enum lru_list lru) { - LIST_HEAD(page_list); + LIST_HEAD(folio_list); unsigned long nr_scanned; - unsigned long nr_reclaimed = 0; + unsigned int nr_reclaimed = 0; unsigned long nr_taken; struct reclaim_stat stat; - int file = is_file_lru(lru); + bool file = is_file_lru(lru); enum vm_event_item item; struct pglist_data *pgdat = lruvec_pgdat(lruvec); - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; bool stalled = false; while (unlikely(too_many_isolated(pgdat, file, sc))) { @@ -1915,8 +2459,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, return 0; /* wait a bit for the reclaimer. */ - msleep(100); stalled = true; + reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED); /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) @@ -1925,51 +2469,47 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, lru_add_drain(); - spin_lock_irq(&pgdat->lru_lock); + spin_lock_irq(&lruvec->lru_lock); - nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list, + 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); - reclaim_stat->recent_scanned[file] += nr_taken; - item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned); - spin_unlock_irq(&pgdat->lru_lock); + __count_vm_events(PGSCAN_ANON + file, nr_scanned); + + spin_unlock_irq(&lruvec->lru_lock); if (nr_taken == 0) return 0; - nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, 0, - &stat, false); + nr_reclaimed = shrink_folio_list(&folio_list, pgdat, sc, &stat, false); - spin_lock_irq(&pgdat->lru_lock); + 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 = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); - reclaim_stat->recent_rotated[0] += stat.nr_activate[0]; - reclaim_stat->recent_rotated[1] += stat.nr_activate[1]; + __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed); + spin_unlock_irq(&lruvec->lru_lock); - move_pages_to_lru(lruvec, &page_list); - - __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); - - spin_unlock_irq(&pgdat->lru_lock); - - mem_cgroup_uncharge_list(&page_list); - free_unref_page_list(&page_list); + lru_note_cost(lruvec, file, stat.nr_pageout); + mem_cgroup_uncharge_list(&folio_list); + free_unref_page_list(&folio_list); /* - * If dirty pages are scanned that are not queued for IO, it + * 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 pages to the end of + * 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 pages grows not through writes but through memory + * 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. @@ -1991,6 +2531,23 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, 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, @@ -1999,11 +2556,9 @@ static void shrink_active_list(unsigned long nr_to_scan, unsigned long nr_taken; unsigned long nr_scanned; unsigned long vm_flags; - LIST_HEAD(l_hold); /* The pages which were snipped off */ + LIST_HEAD(l_hold); /* The folios which were snipped off */ LIST_HEAD(l_active); LIST_HEAD(l_inactive); - struct page *page; - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; unsigned nr_deactivate, nr_activate; unsigned nr_rotated = 0; int file = is_file_lru(lru); @@ -2011,82 +2566,78 @@ static void shrink_active_list(unsigned long nr_to_scan, lru_add_drain(); - spin_lock_irq(&pgdat->lru_lock); + spin_lock_irq(&lruvec->lru_lock); - nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold, + 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); - reclaim_stat->recent_scanned[file] += nr_taken; - __count_vm_events(PGREFILL, nr_scanned); + if (!cgroup_reclaim(sc)) + __count_vm_events(PGREFILL, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned); - spin_unlock_irq(&pgdat->lru_lock); + spin_unlock_irq(&lruvec->lru_lock); while (!list_empty(&l_hold)) { + struct folio *folio; + cond_resched(); - page = lru_to_page(&l_hold); - list_del(&page->lru); + folio = lru_to_folio(&l_hold); + list_del(&folio->lru); - if (unlikely(!page_evictable(page))) { - putback_lru_page(page); + if (unlikely(!folio_evictable(folio))) { + folio_putback_lru(folio); continue; } if (unlikely(buffer_heads_over_limit)) { - if (page_has_private(page) && trylock_page(page)) { - if (page_has_private(page)) - try_to_release_page(page, 0); - unlock_page(page); + if (folio_test_private(folio) && folio_trylock(folio)) { + if (folio_test_private(folio)) + filemap_release_folio(folio, 0); + folio_unlock(folio); } } - if (page_referenced(page, 0, sc->target_mem_cgroup, - &vm_flags)) { - nr_rotated += hpage_nr_pages(page); + /* Referenced or rmap lock contention: rotate */ + if (folio_referenced(folio, 0, sc->target_mem_cgroup, + &vm_flags) != 0) { /* - * Identify referenced, file-backed active pages and + * 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 pages + * 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 pages, + * IO, plus JVM can create lots of anon VM_EXEC folios, * so we ignore them here. */ - if ((vm_flags & VM_EXEC) && page_is_file_cache(page)) { - list_add(&page->lru, &l_active); + if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) { + nr_rotated += folio_nr_pages(folio); + list_add(&folio->lru, &l_active); continue; } } - ClearPageActive(page); /* we are de-activating */ - SetPageWorkingset(page); - list_add(&page->lru, &l_inactive); + folio_clear_active(folio); /* we are de-activating */ + folio_set_workingset(folio); + list_add(&folio->lru, &l_inactive); } /* - * Move pages back to the lru list. + * Move folios back to the lru list. */ - spin_lock_irq(&pgdat->lru_lock); - /* - * Count referenced pages from currently used mappings as rotated, - * even though only some of them are actually re-activated. This - * helps balance scan pressure between file and anonymous pages in - * get_scan_count. - */ - reclaim_stat->recent_rotated[file] += nr_rotated; + spin_lock_irq(&lruvec->lru_lock); - nr_activate = move_pages_to_lru(lruvec, &l_active); - nr_deactivate = move_pages_to_lru(lruvec, &l_inactive); - /* Keep all free pages in l_active list */ + nr_activate = move_folios_to_lru(lruvec, &l_active); + nr_deactivate = move_folios_to_lru(lruvec, &l_inactive); + /* Keep all free folios in l_active list */ list_splice(&l_inactive, &l_active); __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(&pgdat->lru_lock); + spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_list(&l_active); free_unref_page_list(&l_active); @@ -2094,58 +2645,59 @@ static void shrink_active_list(unsigned long nr_to_scan, nr_deactivate, nr_rotated, sc->priority, file); } -unsigned long reclaim_pages(struct list_head *page_list) +static unsigned int reclaim_folio_list(struct list_head *folio_list, + struct pglist_data *pgdat) { - int nid = -1; - unsigned long nr_reclaimed = 0; - LIST_HEAD(node_page_list); struct reclaim_stat dummy_stat; - struct page *page; + unsigned int nr_reclaimed; + struct folio *folio; struct scan_control sc = { .gfp_mask = GFP_KERNEL, - .priority = DEF_PRIORITY, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, + .no_demotion = 1, }; - while (!list_empty(page_list)) { - page = lru_to_page(page_list); - if (nid == -1) { - nid = page_to_nid(page); - INIT_LIST_HEAD(&node_page_list); - } + nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &dummy_stat, false); + while (!list_empty(folio_list)) { + folio = lru_to_folio(folio_list); + list_del(&folio->lru); + folio_putback_lru(folio); + } + + return nr_reclaimed; +} - if (nid == page_to_nid(page)) { - ClearPageActive(page); - list_move(&page->lru, &node_page_list); +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 += shrink_page_list(&node_page_list, - NODE_DATA(nid), - &sc, 0, - &dummy_stat, false); - while (!list_empty(&node_page_list)) { - page = lru_to_page(&node_page_list); - list_del(&page->lru); - putback_lru_page(page); - } + nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); + nid = folio_nid(lru_to_folio(folio_list)); + } while (!list_empty(folio_list)); - nid = -1; - } + nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); - if (!list_empty(&node_page_list)) { - nr_reclaimed += shrink_page_list(&node_page_list, - NODE_DATA(nid), - &sc, 0, - &dummy_stat, false); - while (!list_empty(&node_page_list)) { - page = lru_to_page(&node_page_list); - list_del(&page->lru); - putback_lru_page(page); - } - } + memalloc_noreclaim_restore(noreclaim_flag); return nr_reclaimed; } @@ -2173,13 +2725,13 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, * but large enough to avoid thrashing the aggregate readahead window. * * Both inactive lists should also be large enough that each inactive - * page has a chance to be referenced again before it is reclaimed. + * 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 pages + * 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 pages are kept on the inactive list. + * of 3 means 3:1 or 25% of the folios are kept on the inactive list. * * total target max * memory ratio inactive @@ -2218,32 +2770,134 @@ enum scan_balance { SCAN_FILE, }; +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); + + /* + * Flush the memory cgroup stats, so that we read accurate per-memcg + * lruvec stats for heuristics. + */ + mem_cgroup_flush_stats(); + + /* + * 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->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. The relative value of each set of LRU lists is determined - * by looking at the fraction of the pages scanned we did rotate back - * onto the active list instead of evict. + * scanned. * - * nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan - * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan + * 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); - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; - u64 fraction[2]; + u64 fraction[ANON_AND_FILE]; u64 denominator = 0; /* gcc */ - struct pglist_data *pgdat = lruvec_pgdat(lruvec); - unsigned long anon_prio, file_prio; enum scan_balance scan_balance; - unsigned long anon, file; unsigned long ap, fp; enum lru_list lru; - /* If we have no swap space, do not bother scanning anon pages. */ - if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) { + /* 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; } @@ -2288,69 +2942,47 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, } scan_balance = SCAN_FRACT; - /* - * With swappiness at 100, anonymous and file have the same priority. - * This scanning priority is essentially the inverse of IO cost. - */ - anon_prio = swappiness; - file_prio = 200 - anon_prio; - - /* - * OK, so we have swap space and a fair amount of page cache - * pages. We use the recently rotated / recently scanned - * ratios to determine how valuable each cache is. + * Calculate the pressure balance between anon and file pages. * - * Because workloads change over time (and to avoid overflow) - * we keep these statistics as a floating average, which ends - * up weighing recent references more than old ones. + * 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). * - * anon in [0], file in [1] + * 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; - anon = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON, MAX_NR_ZONES) + - lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, MAX_NR_ZONES); - file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) + - lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES); - - spin_lock_irq(&pgdat->lru_lock); - if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) { - reclaim_stat->recent_scanned[0] /= 2; - reclaim_stat->recent_rotated[0] /= 2; - } - - if (unlikely(reclaim_stat->recent_scanned[1] > file / 4)) { - reclaim_stat->recent_scanned[1] /= 2; - reclaim_stat->recent_rotated[1] /= 2; - } - - /* - * The amount of pressure on anon vs file pages is inversely - * proportional to the fraction of recently scanned pages on - * each list that were recently referenced and in active use. - */ - ap = anon_prio * (reclaim_stat->recent_scanned[0] + 1); - ap /= reclaim_stat->recent_rotated[0] + 1; + ap = swappiness * (total_cost + 1); + ap /= anon_cost + 1; - fp = file_prio * (reclaim_stat->recent_scanned[1] + 1); - fp /= reclaim_stat->recent_rotated[1] + 1; - spin_unlock_irq(&pgdat->lru_lock); + fp = (200 - swappiness) * (total_cost + 1); + fp /= file_cost + 1; fraction[0] = ap; fraction[1] = fp; - denominator = ap + fp + 1; + denominator = ap + fp; out: for_each_evictable_lru(lru) { int file = is_file_lru(lru); unsigned long lruvec_size; + unsigned long low, min; unsigned long scan; - unsigned long protection; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); - protection = mem_cgroup_protection(memcg, - sc->memcg_low_reclaim); + mem_cgroup_protection(sc->target_mem_cgroup, memcg, + &min, &low); - if (protection) { + if (min || low) { /* * Scale a cgroup's reclaim pressure by proportioning * its current usage to its memory.low or memory.min @@ -2381,16 +3013,25 @@ out: * 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; + (cgroup_size + 1); /* * Minimally target SWAP_CLUSTER_MAX pages to keep - * reclaim moving forwards, avoiding decremeting + * reclaim moving forwards, avoiding decrementing * sc->priority further than desirable. */ scan = max(scan, SWAP_CLUSTER_MAX); @@ -2427,10 +3068,8 @@ out: case SCAN_FILE: case SCAN_ANON: /* Scan one type exclusively */ - if ((scan_balance == SCAN_FILE) != file) { - lruvec_size = 0; + if ((scan_balance == SCAN_FILE) != file) scan = 0; - } break; default: /* Look ma, no brain */ @@ -2441,6 +3080,2762 @@ out: } } +/* + * 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 + +/****************************************************************************** + * 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)++) + +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; + + /* for hotadd_new_pgdat() */ + if (!lruvec->pgdat) + lruvec->pgdat = pgdat; + + return lruvec; + } +#endif + VM_WARN_ON_ONCE(!mem_cgroup_disabled()); + + 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; +} + +/****************************************************************************** + * mm_struct list + ******************************************************************************/ + +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; +} + +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); + + if (!lruvec) + continue; + + /* the first addition since the last iteration */ + if (lruvec->mm_state.tail == &mm_list->fifo) + lruvec->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); + + if (!lruvec) + continue; + + /* where the last iteration ended (exclusive) */ + if (lruvec->mm_state.tail == &mm->lru_gen.list) + lruvec->mm_state.tail = lruvec->mm_state.tail->next; + + /* where the current iteration continues (inclusive) */ + if (lruvec->mm_state.head != &mm->lru_gen.list) + continue; + + lruvec->mm_state.head = lruvec->mm_state.head->next; + /* the deletion ends the current iteration */ + if (lruvec->mm_state.head == &mm_list->fifo) + WRITE_ONCE(lruvec->mm_state.seq, lruvec->mm_state.seq + 1); + } + + 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; + + rcu_read_lock(); + memcg = mem_cgroup_from_task(task); + rcu_read_unlock(); + if (memcg == mm->lru_gen.memcg) + return; + + VM_WARN_ON_ONCE(!mm->lru_gen.memcg); + VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list)); + + lru_gen_del_mm(mm); + lru_gen_add_mm(mm); +} +#endif + +/* + * 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 void reset_bloom_filter(struct lruvec *lruvec, unsigned long seq) +{ + unsigned long *filter; + int gen = filter_gen_from_seq(seq); + + filter = lruvec->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(lruvec->mm_state.filters[gen], filter); +} + +static void update_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *item) +{ + int key[2]; + unsigned long *filter; + int gen = filter_gen_from_seq(seq); + + filter = READ_ONCE(lruvec->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 bool test_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *item) +{ + int key[2]; + unsigned long *filter; + int gen = filter_gen_from_seq(seq); + + filter = READ_ONCE(lruvec->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 reset_mm_stats(struct lruvec *lruvec, struct lru_gen_mm_walk *walk, bool last) +{ + int i; + int hist; + + lockdep_assert_held(&get_mm_list(lruvec_memcg(lruvec))->lock); + + if (walk) { + hist = lru_hist_from_seq(walk->max_seq); + + for (i = 0; i < NR_MM_STATS; i++) { + WRITE_ONCE(lruvec->mm_state.stats[hist][i], + lruvec->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(lruvec->mm_state.seq + 1); + + for (i = 0; i < NR_MM_STATS; i++) + WRITE_ONCE(lruvec->mm_state.stats[hist][i], 0); + } +} + +static bool should_skip_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk) +{ + int type; + unsigned long size = 0; + struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); + int key = pgdat->node_id % BITS_PER_TYPE(mm->lru_gen.bitmap); + + if (!walk->force_scan && !test_bit(key, &mm->lru_gen.bitmap)) + return true; + + clear_bit(key, &mm->lru_gen.bitmap); + + for (type = !walk->can_swap; type < ANON_AND_FILE; type++) { + size += type ? get_mm_counter(mm, MM_FILEPAGES) : + get_mm_counter(mm, MM_ANONPAGES) + + get_mm_counter(mm, MM_SHMEMPAGES); + } + + if (size < MIN_LRU_BATCH) + return true; + + return !mmget_not_zero(mm); +} + +static bool iterate_mm_list(struct lruvec *lruvec, struct lru_gen_mm_walk *walk, + struct mm_struct **iter) +{ + bool first = false; + bool last = true; + struct mm_struct *mm = NULL; + 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 = &lruvec->mm_state; + + /* + * There are four interesting cases for this page table walker: + * 1. It tries to start a new iteration of mm_list with a stale max_seq; + * there is nothing left to do. + * 2. It's the first of the current generation, and it needs to reset + * the Bloom filter for the next generation. + * 3. It reaches the end of mm_list, and it needs to increment + * mm_state->seq; the iteration is done. + * 4. It's the last of the current generation, and it needs to reset the + * mm stats counters for the next generation. + */ + spin_lock(&mm_list->lock); + + VM_WARN_ON_ONCE(mm_state->seq + 1 < walk->max_seq); + VM_WARN_ON_ONCE(*iter && mm_state->seq > walk->max_seq); + VM_WARN_ON_ONCE(*iter && !mm_state->nr_walkers); + + if (walk->max_seq <= mm_state->seq) { + if (!*iter) + last = false; + goto done; + } + + if (!mm_state->nr_walkers) { + VM_WARN_ON_ONCE(mm_state->head && mm_state->head != &mm_list->fifo); + + mm_state->head = mm_list->fifo.next; + first = true; + } + + while (!mm && mm_state->head != &mm_list->fifo) { + mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list); + + mm_state->head = mm_state->head->next; + + /* force scan for those added after the last iteration */ + if (!mm_state->tail || mm_state->tail == &mm->lru_gen.list) { + mm_state->tail = mm_state->head; + walk->force_scan = true; + } + + if (should_skip_mm(mm, walk)) + mm = NULL; + } + + if (mm_state->head == &mm_list->fifo) + WRITE_ONCE(mm_state->seq, mm_state->seq + 1); +done: + if (*iter && !mm) + mm_state->nr_walkers--; + if (!*iter && mm) + mm_state->nr_walkers++; + + if (mm_state->nr_walkers) + last = false; + + if (*iter || last) + reset_mm_stats(lruvec, walk, last); + + spin_unlock(&mm_list->lock); + + if (mm && first) + reset_bloom_filter(lruvec, walk->max_seq + 1); + + if (*iter) + mmput_async(*iter); + + *iter = mm; + + return last; +} + +static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long max_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 = &lruvec->mm_state; + + spin_lock(&mm_list->lock); + + VM_WARN_ON_ONCE(mm_state->seq + 1 < max_seq); + + if (max_seq > mm_state->seq && !mm_state->nr_walkers) { + VM_WARN_ON_ONCE(mm_state->head && mm_state->head != &mm_list->fifo); + + WRITE_ONCE(mm_state->seq, mm_state->seq + 1); + reset_mm_stats(lruvec, NULL, true); + success = true; + } + + spin_unlock(&mm_list->lock); + + return success; +} + +/****************************************************************************** + * 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 + ******************************************************************************/ + +/* 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_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_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 lruvec *lruvec, struct lru_gen_mm_walk *walk) +{ + int gen, type, zone; + struct lru_gen_struct *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->vm_flags & (VM_LOCKED | VM_SPECIAL | VM_SEQ_READ | VM_RAND_READ)) + 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; +} + +static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr) +{ + unsigned long pfn = pte_pfn(pte); + + VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); + + if (!pte_present(pte) || is_zero_pfn(pfn)) + return -1; + + if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte))) + return -1; + + if (WARN_ON_ONCE(!pfn_valid(pfn))) + return -1; + + return pfn; +} + +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) +static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr) +{ + unsigned long pfn = pmd_pfn(pmd); + + VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); + + if (!pmd_present(pmd) || is_huge_zero_pmd(pmd)) + return -1; + + if (WARN_ON_ONCE(pmd_devmap(pmd))) + return -1; + + if (WARN_ON_ONCE(!pfn_valid(pfn))) + return -1; + + return pfn; +} +#endif + +static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg, + struct pglist_data *pgdat, bool can_swap) +{ + struct folio *folio; + + /* try to avoid unnecessary memory loads */ + if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) + return NULL; + + folio = pfn_folio(pfn); + if (folio_nid(folio) != pgdat->node_id) + return NULL; + + if (folio_memcg_rcu(folio) != memcg) + return NULL; + + /* file VMAs can contain anon pages from COW */ + if (!folio_is_file_lru(folio) && !can_swap) + return NULL; + + return folio; +} + +static bool suitable_to_scan(int total, int young) +{ + int n = clamp_t(int, cache_line_size() / sizeof(pte_t), 2, 8); + + /* suitable if the average number of young PTEs per cacheline is >=1 */ + return young * n >= total; +} + +static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end, + struct mm_walk *args) +{ + int i; + pte_t *pte; + spinlock_t *ptl; + unsigned long addr; + int total = 0; + int young = 0; + struct lru_gen_mm_walk *walk = args->private; + struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); + struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); + int old_gen, new_gen = lru_gen_from_seq(walk->max_seq); + + VM_WARN_ON_ONCE(pmd_leaf(*pmd)); + + ptl = pte_lockptr(args->mm, pmd); + if (!spin_trylock(ptl)) + return false; + + arch_enter_lazy_mmu_mode(); + + pte = pte_offset_map(pmd, start & PMD_MASK); +restart: + for (i = pte_index(start), addr = start; addr != end; i++, addr += PAGE_SIZE) { + unsigned long pfn; + struct folio *folio; + + total++; + walk->mm_stats[MM_LEAF_TOTAL]++; + + pfn = get_pte_pfn(pte[i], args->vma, addr); + if (pfn == -1) + continue; + + if (!pte_young(pte[i])) { + walk->mm_stats[MM_LEAF_OLD]++; + continue; + } + + folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); + if (!folio) + continue; + + if (!ptep_test_and_clear_young(args->vma, addr, pte + i)) + VM_WARN_ON_ONCE(true); + + young++; + walk->mm_stats[MM_LEAF_YOUNG]++; + + if (pte_dirty(pte[i]) && !folio_test_dirty(folio) && + !(folio_test_anon(folio) && folio_test_swapbacked(folio) && + !folio_test_swapcache(folio))) + folio_mark_dirty(folio); + + old_gen = folio_update_gen(folio, new_gen); + if (old_gen >= 0 && old_gen != new_gen) + update_batch_size(walk, folio, old_gen, new_gen); + } + + if (i < PTRS_PER_PTE && get_next_vma(PMD_MASK, PAGE_SIZE, args, &start, &end)) + goto restart; + + pte_unmap(pte); + + arch_leave_lazy_mmu_mode(); + spin_unlock(ptl); + + return suitable_to_scan(total, young); +} + +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) +static void walk_pmd_range_locked(pud_t *pud, unsigned long next, struct vm_area_struct *vma, + struct mm_walk *args, unsigned long *bitmap, unsigned long *start) +{ + int i; + pmd_t *pmd; + spinlock_t *ptl; + struct lru_gen_mm_walk *walk = args->private; + struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); + struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); + int old_gen, new_gen = lru_gen_from_seq(walk->max_seq); + + VM_WARN_ON_ONCE(pud_leaf(*pud)); + + /* try to batch at most 1+MIN_LRU_BATCH+1 entries */ + if (*start == -1) { + *start = next; + return; + } + + i = next == -1 ? 0 : pmd_index(next) - pmd_index(*start); + if (i && i <= MIN_LRU_BATCH) { + __set_bit(i - 1, bitmap); + return; + } + + pmd = pmd_offset(pud, *start); + + ptl = pmd_lockptr(args->mm, pmd); + if (!spin_trylock(ptl)) + goto done; + + arch_enter_lazy_mmu_mode(); + + do { + unsigned long pfn; + struct folio *folio; + unsigned long addr = i ? (*start & PMD_MASK) + i * PMD_SIZE : *start; + + pfn = get_pmd_pfn(pmd[i], vma, addr); + if (pfn == -1) + goto next; + + if (!pmd_trans_huge(pmd[i])) { + if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) && + get_cap(LRU_GEN_NONLEAF_YOUNG)) + pmdp_test_and_clear_young(vma, addr, pmd + i); + goto next; + } + + folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); + if (!folio) + goto next; + + if (!pmdp_test_and_clear_young(vma, addr, pmd + i)) + goto next; + + walk->mm_stats[MM_LEAF_YOUNG]++; + + if (pmd_dirty(pmd[i]) && !folio_test_dirty(folio) && + !(folio_test_anon(folio) && folio_test_swapbacked(folio) && + !folio_test_swapcache(folio))) + folio_mark_dirty(folio); + + old_gen = folio_update_gen(folio, new_gen); + if (old_gen >= 0 && old_gen != new_gen) + update_batch_size(walk, folio, old_gen, new_gen); +next: + i = i > MIN_LRU_BATCH ? 0 : find_next_bit(bitmap, MIN_LRU_BATCH, i) + 1; + } while (i <= MIN_LRU_BATCH); + + arch_leave_lazy_mmu_mode(); + spin_unlock(ptl); +done: + *start = -1; + bitmap_zero(bitmap, MIN_LRU_BATCH); +} +#else +static void walk_pmd_range_locked(pud_t *pud, unsigned long next, struct vm_area_struct *vma, + struct mm_walk *args, unsigned long *bitmap, unsigned long *start) +{ +} +#endif + +static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end, + struct mm_walk *args) +{ + int i; + pmd_t *pmd; + unsigned long next; + unsigned long addr; + struct vm_area_struct *vma; + unsigned long pos = -1; + struct lru_gen_mm_walk *walk = args->private; + unsigned long bitmap[BITS_TO_LONGS(MIN_LRU_BATCH)] = {}; + + VM_WARN_ON_ONCE(pud_leaf(*pud)); + + /* + * Finish an entire PMD in two passes: the first only reaches to PTE + * tables to avoid taking the PMD lock; the second, if necessary, takes + * the PMD lock to clear the accessed bit in PMD entries. + */ + pmd = pmd_offset(pud, start & PUD_MASK); +restart: + /* walk_pte_range() may call get_next_vma() */ + vma = args->vma; + for (i = pmd_index(start), addr = start; addr != end; i++, addr = next) { + pmd_t val = pmd_read_atomic(pmd + i); + + /* for pmd_read_atomic() */ + barrier(); + + next = pmd_addr_end(addr, end); + + if (!pmd_present(val) || is_huge_zero_pmd(val)) { + walk->mm_stats[MM_LEAF_TOTAL]++; + continue; + } + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (pmd_trans_huge(val)) { + unsigned long pfn = pmd_pfn(val); + struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); + + walk->mm_stats[MM_LEAF_TOTAL]++; + + if (!pmd_young(val)) { + walk->mm_stats[MM_LEAF_OLD]++; + continue; + } + + /* try to avoid unnecessary memory loads */ + if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) + continue; + + walk_pmd_range_locked(pud, addr, vma, args, bitmap, &pos); + continue; + } +#endif + walk->mm_stats[MM_NONLEAF_TOTAL]++; + +#ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG + if (get_cap(LRU_GEN_NONLEAF_YOUNG)) { + if (!pmd_young(val)) + continue; + + walk_pmd_range_locked(pud, addr, vma, args, bitmap, &pos); + } +#endif + if (!walk->force_scan && !test_bloom_filter(walk->lruvec, walk->max_seq, pmd + i)) + continue; + + walk->mm_stats[MM_NONLEAF_FOUND]++; + + if (!walk_pte_range(&val, addr, next, args)) + continue; + + walk->mm_stats[MM_NONLEAF_ADDED]++; + + /* carry over to the next generation */ + update_bloom_filter(walk->lruvec, walk->max_seq + 1, pmd + i); + } + + walk_pmd_range_locked(pud, -1, vma, args, bitmap, &pos); + + if (i < PTRS_PER_PMD && get_next_vma(PUD_MASK, PMD_SIZE, args, &start, &end)) + goto restart; +} + +static int walk_pud_range(p4d_t *p4d, unsigned long start, unsigned long end, + struct mm_walk *args) +{ + int i; + pud_t *pud; + unsigned long addr; + unsigned long next; + struct lru_gen_mm_walk *walk = args->private; + + VM_WARN_ON_ONCE(p4d_leaf(*p4d)); + + pud = pud_offset(p4d, start & P4D_MASK); +restart: + for (i = pud_index(start), addr = start; addr != end; i++, addr = next) { + pud_t val = READ_ONCE(pud[i]); + + next = pud_addr_end(addr, end); + + if (!pud_present(val) || WARN_ON_ONCE(pud_leaf(val))) + continue; + + walk_pmd_range(&val, addr, next, args); + + /* a racy check to curtail the waiting time */ + if (wq_has_sleeper(&walk->lruvec->mm_state.wait)) + return 1; + + if (need_resched() || walk->batched >= MAX_LRU_BATCH) { + end = (addr | ~PUD_MASK) + 1; + goto done; + } + } + + if (i < PTRS_PER_PUD && get_next_vma(P4D_MASK, PUD_SIZE, args, &start, &end)) + goto restart; + + end = round_up(end, P4D_SIZE); +done: + if (!end || !args->vma) + return 1; + + walk->next_addr = max(end, args->vma->vm_start); + + return -EAGAIN; +} + +static void walk_mm(struct lruvec *lruvec, struct mm_struct *mm, struct lru_gen_mm_walk *walk) +{ + static const struct mm_walk_ops mm_walk_ops = { + .test_walk = should_skip_vma, + .p4d_entry = walk_pud_range, + }; + + int err; + struct mem_cgroup *memcg = lruvec_memcg(lruvec); + + walk->next_addr = FIRST_USER_ADDRESS; + + do { + err = -EBUSY; + + /* folio_update_gen() requires stable folio_memcg() */ + if (!mem_cgroup_trylock_pages(memcg)) + break; + + /* the caller might be holding the lock for write */ + if (mmap_read_trylock(mm)) { + err = walk_page_range(mm, walk->next_addr, ULONG_MAX, &mm_walk_ops, walk); + + mmap_read_unlock(mm); + } + + mem_cgroup_unlock_pages(); + + if (walk->batched) { + spin_lock_irq(&lruvec->lru_lock); + reset_batch_size(lruvec, walk); + spin_unlock_irq(&lruvec->lru_lock); + } + + cond_resched(); + } while (err == -EAGAIN); +} + +static struct lru_gen_mm_walk *set_mm_walk(struct pglist_data *pgdat) +{ + struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; + + if (pgdat && current_is_kswapd()) { + VM_WARN_ON_ONCE(walk); + + walk = &pgdat->mm_walk; + } else if (!pgdat && !walk) { + VM_WARN_ON_ONCE(current_is_kswapd()); + + walk = kzalloc(sizeof(*walk), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); + } + + current->reclaim_state->mm_walk = walk; + + return walk; +} + +static void clear_mm_walk(void) +{ + struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; + + VM_WARN_ON_ONCE(walk && memchr_inv(walk->nr_pages, 0, sizeof(walk->nr_pages))); + VM_WARN_ON_ONCE(walk && memchr_inv(walk->mm_stats, 0, sizeof(walk->mm_stats))); + + current->reclaim_state->mm_walk = NULL; + + if (!current_is_kswapd()) + kfree(walk); +} + +static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap) +{ + int zone; + int remaining = MAX_LRU_BATCH; + struct lru_gen_struct *lrugen = &lruvec->lrugen; + int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); + + if (type == LRU_GEN_ANON && !can_swap) + goto done; + + /* prevent cold/hot inversion if force_scan is true */ + for (zone = 0; zone < MAX_NR_ZONES; zone++) { + struct list_head *head = &lrugen->lists[old_gen][type][zone]; + + while (!list_empty(head)) { + struct folio *folio = lru_to_folio(head); + + 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); + + new_gen = folio_inc_gen(lruvec, folio, false); + list_move_tail(&folio->lru, &lrugen->lists[new_gen][type][zone]); + + if (!--remaining) + return false; + } + } +done: + reset_ctrl_pos(lruvec, type, true); + WRITE_ONCE(lrugen->min_seq[type], lrugen->min_seq[type] + 1); + + return true; +} + +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, bool can_swap, bool force_scan) +{ + 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)); + + for (type = ANON_AND_FILE - 1; type >= 0; type--) { + if (get_nr_gens(lruvec, type) != MAX_NR_GENS) + continue; + + VM_WARN_ON_ONCE(!force_scan && (type == LRU_GEN_FILE || can_swap)); + + while (!inc_min_seq(lruvec, type, can_swap)) { + spin_unlock_irq(&lruvec->lru_lock); + cond_resched(); + spin_lock_irq(&lruvec->lru_lock); + } + } + + /* + * 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); + + WRITE_ONCE(lrugen->timestamps[next], jiffies); + /* make sure preceding modifications appear */ + smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1); + + spin_unlock_irq(&lruvec->lru_lock); +} + +static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq, + struct scan_control *sc, bool can_swap, bool force_scan) +{ + bool success; + struct lru_gen_mm_walk *walk; + struct mm_struct *mm = NULL; + struct lru_gen_struct *lrugen = &lruvec->lrugen; + + VM_WARN_ON_ONCE(max_seq > READ_ONCE(lrugen->max_seq)); + + /* see the comment in iterate_mm_list() */ + if (max_seq <= READ_ONCE(lruvec->mm_state.seq)) { + success = false; + goto done; + } + + /* + * If the hardware doesn't automatically set the accessed bit, fallback + * to lru_gen_look_around(), which only clears the accessed bit in a + * handful of PTEs. Spreading the work out over a period of time usually + * is less efficient, but it avoids bursty page faults. + */ + if (!force_scan && !(arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK))) { + success = iterate_mm_list_nowalk(lruvec, max_seq); + goto done; + } + + walk = set_mm_walk(NULL); + if (!walk) { + success = iterate_mm_list_nowalk(lruvec, max_seq); + goto done; + } + + walk->lruvec = lruvec; + walk->max_seq = max_seq; + walk->can_swap = can_swap; + walk->force_scan = force_scan; + + do { + success = iterate_mm_list(lruvec, walk, &mm); + if (mm) + walk_mm(lruvec, mm, walk); + + cond_resched(); + } while (mm); +done: + if (!success) { + if (sc->priority <= DEF_PRIORITY - 2) + wait_event_killable(lruvec->mm_state.wait, + max_seq < READ_ONCE(lrugen->max_seq)); + + return max_seq < READ_ONCE(lrugen->max_seq); + } + + VM_WARN_ON_ONCE(max_seq != READ_ONCE(lrugen->max_seq)); + + inc_max_seq(lruvec, can_swap, force_scan); + /* either this sees any waiters or they will see updated max_seq */ + if (wq_has_sleeper(&lruvec->mm_state.wait)) + wake_up_all(&lruvec->mm_state.wait); + + return true; +} + +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 bool age_lruvec(struct lruvec *lruvec, struct scan_control *sc, unsigned long min_ttl) +{ + 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 false; + + need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, swappiness, &nr_to_scan); + + if (min_ttl) { + int gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]); + unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); + + if (time_is_after_jiffies(birth + min_ttl)) + return false; + + /* the size is likely too small to be helpful */ + if (!nr_to_scan && sc->priority != DEF_PRIORITY) + return false; + } + + if (need_aging) + try_to_inc_max_seq(lruvec, max_seq, sc, swappiness, false); + + return true; +} + +/* to protect the working set of the last N jiffies */ +static unsigned long lru_gen_min_ttl __read_mostly; + +static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) +{ + struct mem_cgroup *memcg; + bool success = false; + unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl); + + VM_WARN_ON_ONCE(!current_is_kswapd()); + + sc->last_reclaimed = sc->nr_reclaimed; + + /* + * To reduce the chance of going into the aging path, which can be + * costly, optimistically skip it if the flag below was cleared in the + * eviction path. This improves the overall performance when multiple + * memcgs are available. + */ + if (!sc->memcgs_need_aging) { + sc->memcgs_need_aging = true; + return; + } + + set_mm_walk(pgdat); + + memcg = mem_cgroup_iter(NULL, NULL, NULL); + do { + struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); + + if (age_lruvec(lruvec, sc, min_ttl)) + success = true; + + cond_resched(); + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); + + clear_mm_walk(); + + /* check the order to exclude compaction-induced reclaim */ + if (success || !min_ttl || sc->order) + return; + + /* + * The main goal is to OOM kill if every generation from all memcgs is + * younger than min_ttl. However, another possibility is all memcgs are + * either below min or empty. + */ + if (mutex_trylock(&oom_lock)) { + struct oom_control oc = { + .gfp_mask = sc->gfp_mask, + }; + + out_of_memory(&oc); + + mutex_unlock(&oom_lock); + } +} + +/* + * This function exploits spatial locality when shrink_folio_list() walks the + * rmap. It scans the adjacent PTEs of a young PTE and promotes hot pages. If + * the scan was done cacheline efficiently, it adds the PMD entry pointing to + * the PTE table to the Bloom filter. This forms a feedback loop between the + * eviction and the aging. + */ +void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +{ + int i; + pte_t *pte; + unsigned long start; + unsigned long end; + unsigned long addr; + struct lru_gen_mm_walk *walk; + int young = 0; + unsigned long bitmap[BITS_TO_LONGS(MIN_LRU_BATCH)] = {}; + struct folio *folio = pfn_folio(pvmw->pfn); + struct mem_cgroup *memcg = folio_memcg(folio); + struct pglist_data *pgdat = folio_pgdat(folio); + struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); + DEFINE_MAX_SEQ(lruvec); + int old_gen, new_gen = lru_gen_from_seq(max_seq); + + lockdep_assert_held(pvmw->ptl); + VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio); + + if (spin_is_contended(pvmw->ptl)) + return; + + /* avoid taking the LRU lock under the PTL when possible */ + walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL; + + start = max(pvmw->address & PMD_MASK, pvmw->vma->vm_start); + end = min(pvmw->address | ~PMD_MASK, pvmw->vma->vm_end - 1) + 1; + + if (end - start > MIN_LRU_BATCH * PAGE_SIZE) { + if (pvmw->address - start < MIN_LRU_BATCH * PAGE_SIZE / 2) + end = start + MIN_LRU_BATCH * PAGE_SIZE; + else if (end - pvmw->address < MIN_LRU_BATCH * PAGE_SIZE / 2) + start = end - MIN_LRU_BATCH * PAGE_SIZE; + else { + start = pvmw->address - MIN_LRU_BATCH * PAGE_SIZE / 2; + end = pvmw->address + MIN_LRU_BATCH * PAGE_SIZE / 2; + } + } + + pte = pvmw->pte - (pvmw->address - start) / PAGE_SIZE; + + rcu_read_lock(); + arch_enter_lazy_mmu_mode(); + + for (i = 0, addr = start; addr != end; i++, addr += PAGE_SIZE) { + unsigned long pfn; + + pfn = get_pte_pfn(pte[i], pvmw->vma, addr); + if (pfn == -1) + continue; + + if (!pte_young(pte[i])) + continue; + + folio = get_pfn_folio(pfn, memcg, pgdat, !walk || walk->can_swap); + if (!folio) + continue; + + if (!ptep_test_and_clear_young(pvmw->vma, addr, pte + i)) + VM_WARN_ON_ONCE(true); + + young++; + + if (pte_dirty(pte[i]) && !folio_test_dirty(folio) && + !(folio_test_anon(folio) && folio_test_swapbacked(folio) && + !folio_test_swapcache(folio))) + folio_mark_dirty(folio); + + old_gen = folio_lru_gen(folio); + if (old_gen < 0) + folio_set_referenced(folio); + else if (old_gen != new_gen) + __set_bit(i, bitmap); + } + + arch_leave_lazy_mmu_mode(); + rcu_read_unlock(); + + /* feedback from rmap walkers to page table walkers */ + if (suitable_to_scan(i, young)) + update_bloom_filter(lruvec, max_seq, pvmw->pmd); + + if (!walk && bitmap_weight(bitmap, MIN_LRU_BATCH) < PAGEVEC_SIZE) { + for_each_set_bit(i, bitmap, MIN_LRU_BATCH) { + folio = pfn_folio(pte_pfn(pte[i])); + folio_activate(folio); + } + return; + } + + /* folio_update_gen() requires stable folio_memcg() */ + if (!mem_cgroup_trylock_pages(memcg)) + return; + + if (!walk) { + spin_lock_irq(&lruvec->lru_lock); + new_gen = lru_gen_from_seq(lruvec->lrugen.max_seq); + } + + for_each_set_bit(i, bitmap, MIN_LRU_BATCH) { + folio = pfn_folio(pte_pfn(pte[i])); + if (folio_memcg_rcu(folio) != memcg) + continue; + + old_gen = folio_update_gen(folio, new_gen); + if (old_gen < 0 || old_gen == new_gen) + continue; + + if (walk) + update_batch_size(walk, folio, old_gen, new_gen); + else + lru_gen_update_size(lruvec, folio, old_gen, new_gen); + } + + if (!walk) + spin_unlock_irq(&lruvec->lru_lock); + + mem_cgroup_unlock_pages(); +} + +/****************************************************************************** + * 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; + } + + /* promoted */ + if (gen != lru_gen_from_seq(lrugen->min_seq[type])) { + list_move(&folio->lru, &lrugen->lists[gen][type][zone]); + 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_folio_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, + bool *need_swapping) +{ + int type; + int scanned; + int reclaimed; + LIST_HEAD(list); + struct folio *folio; + enum vm_event_item item; + struct reclaim_stat stat; + struct lru_gen_mm_walk *walk; + 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_folio_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_folios_to_lru(lruvec, &list); + + walk = current->reclaim_state->mm_walk; + if (walk && walk->batched) + reset_batch_size(lruvec, walk); + + 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; + + if (need_swapping && type == LRU_GEN_ANON) + *need_swapping = true; + + return scanned; +} + +/* + * For future optimizations: + * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg + * reclaim. + */ +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; + + if (try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false)) + return nr_to_scan; +done: + return min_seq[!can_swap] + MIN_NR_GENS <= max_seq ? nr_to_scan : 0; +} + +static bool should_abort_scan(struct lruvec *lruvec, unsigned long seq, + struct scan_control *sc, bool need_swapping) +{ + int i; + DEFINE_MAX_SEQ(lruvec); + + if (!current_is_kswapd()) { + /* age each memcg at most once to ensure fairness */ + if (max_seq - seq > 1) + return true; + + /* over-swapping can increase allocation latency */ + if (sc->nr_reclaimed >= sc->nr_to_reclaim && need_swapping) + return true; + + /* give this thread a chance to exit and free its memory */ + if (fatal_signal_pending(current)) { + sc->nr_reclaimed += MIN_LRU_BATCH; + return true; + } + + if (cgroup_reclaim(sc)) + return false; + } else if (sc->nr_reclaimed - sc->last_reclaimed < sc->nr_to_reclaim) + return false; + + /* keep scanning at low priorities to ensure fairness */ + if (sc->priority > DEF_PRIORITY - 2) + return false; + + /* + * A minimum amount of work was done under global memory pressure. For + * kswapd, it may be overshooting. For direct reclaim, the allocation + * may succeed if all suitable zones are somewhat safe. In either case, + * it's better to stop now, and restart later if necessary. + */ + for (i = 0; i <= sc->reclaim_idx; i++) { + unsigned long wmark; + struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i; + + if (!managed_zone(zone)) + continue; + + wmark = current_is_kswapd() ? high_wmark_pages(zone) : low_wmark_pages(zone); + if (wmark > zone_page_state(zone, NR_FREE_PAGES)) + return false; + } + + sc->nr_reclaimed += MIN_LRU_BATCH; + + return true; +} + +static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) +{ + struct blk_plug plug; + bool need_aging = false; + bool need_swapping = false; + unsigned long scanned = 0; + unsigned long reclaimed = sc->nr_reclaimed; + DEFINE_MAX_SEQ(lruvec); + + lru_add_drain(); + + blk_start_plug(&plug); + + set_mm_walk(lruvec_pgdat(lruvec)); + + 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, &need_aging); + if (!nr_to_scan) + goto done; + + delta = evict_folios(lruvec, sc, swappiness, &need_swapping); + if (!delta) + goto done; + + scanned += delta; + if (scanned >= nr_to_scan) + break; + + if (should_abort_scan(lruvec, max_seq, sc, need_swapping)) + break; + + cond_resched(); + } + + /* see the comment in lru_gen_age_node() */ + if (sc->nr_reclaimed - reclaimed >= MIN_LRU_BATCH && !need_aging) + sc->memcgs_need_aging = false; +done: + clear_mm_walk(); + + blk_finish_plug(&plug); +} + +/****************************************************************************** + * state change + ******************************************************************************/ + +static bool __maybe_unused state_is_valid(struct lruvec *lruvec) +{ + struct lru_gen_struct *lrugen = &lruvec->lrugen; + + if (lrugen->enabled) { + enum lru_list lru; + + for_each_evictable_lru(lru) { + if (!list_empty(&lruvec->lists[lru])) + return false; + } + } else { + int gen, type, zone; + + for_each_gen_type_zone(gen, type, zone) { + if (!list_empty(&lrugen->lists[gen][type][zone])) + return false; + } + } + + return true; +} + +static bool fill_evictable(struct lruvec *lruvec) +{ + enum lru_list lru; + int remaining = MAX_LRU_BATCH; + + for_each_evictable_lru(lru) { + int type = is_file_lru(lru); + bool active = is_active_lru(lru); + struct list_head *head = &lruvec->lists[lru]; + + while (!list_empty(head)) { + bool success; + struct folio *folio = lru_to_folio(head); + + VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); + VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio) != active, folio); + VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); + VM_WARN_ON_ONCE_FOLIO(folio_lru_gen(folio) != -1, folio); + + lruvec_del_folio(lruvec, folio); + success = lru_gen_add_folio(lruvec, folio, false); + VM_WARN_ON_ONCE(!success); + + if (!--remaining) + return false; + } + } + + return true; +} + +static bool drain_evictable(struct lruvec *lruvec) +{ + int gen, type, zone; + int remaining = MAX_LRU_BATCH; + + for_each_gen_type_zone(gen, type, zone) { + struct list_head *head = &lruvec->lrugen.lists[gen][type][zone]; + + while (!list_empty(head)) { + bool success; + struct folio *folio = lru_to_folio(head); + + 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); + + success = lru_gen_del_folio(lruvec, folio, false); + VM_WARN_ON_ONCE(!success); + lruvec_add_folio(lruvec, folio); + + if (!--remaining) + return false; + } + } + + return true; +} + +static void lru_gen_change_state(bool enabled) +{ + static DEFINE_MUTEX(state_mutex); + + struct mem_cgroup *memcg; + + cgroup_lock(); + cpus_read_lock(); + get_online_mems(); + mutex_lock(&state_mutex); + + if (enabled == lru_gen_enabled()) + goto unlock; + + if (enabled) + static_branch_enable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); + else + static_branch_disable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); + + memcg = mem_cgroup_iter(NULL, NULL, NULL); + do { + int nid; + + for_each_node(nid) { + struct lruvec *lruvec = get_lruvec(memcg, nid); + + if (!lruvec) + continue; + + spin_lock_irq(&lruvec->lru_lock); + + VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); + VM_WARN_ON_ONCE(!state_is_valid(lruvec)); + + lruvec->lrugen.enabled = enabled; + + while (!(enabled ? fill_evictable(lruvec) : drain_evictable(lruvec))) { + spin_unlock_irq(&lruvec->lru_lock); + cond_resched(); + spin_lock_irq(&lruvec->lru_lock); + } + + spin_unlock_irq(&lruvec->lru_lock); + } + + cond_resched(); + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); +unlock: + mutex_unlock(&state_mutex); + put_online_mems(); + cpus_read_unlock(); + cgroup_unlock(); +} + +/****************************************************************************** + * sysfs interface + ******************************************************************************/ + +static ssize_t show_min_ttl(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl))); +} + +/* see Documentation/admin-guide/mm/multigen_lru.rst for details */ +static ssize_t store_min_ttl(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t len) +{ + unsigned int msecs; + + if (kstrtouint(buf, 0, &msecs)) + return -EINVAL; + + WRITE_ONCE(lru_gen_min_ttl, msecs_to_jiffies(msecs)); + + return len; +} + +static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR( + min_ttl_ms, 0644, show_min_ttl, store_min_ttl +); + +static ssize_t show_enabled(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + unsigned int caps = 0; + + if (get_cap(LRU_GEN_CORE)) + caps |= BIT(LRU_GEN_CORE); + + if (arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK)) + caps |= BIT(LRU_GEN_MM_WALK); + + if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) && get_cap(LRU_GEN_NONLEAF_YOUNG)) + caps |= BIT(LRU_GEN_NONLEAF_YOUNG); + + return snprintf(buf, PAGE_SIZE, "0x%04x\n", caps); +} + +/* see Documentation/admin-guide/mm/multigen_lru.rst for details */ +static ssize_t store_enabled(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t len) +{ + int i; + unsigned int caps; + + if (tolower(*buf) == 'n') + caps = 0; + else if (tolower(*buf) == 'y') + caps = -1; + else if (kstrtouint(buf, 0, &caps)) + return -EINVAL; + + for (i = 0; i < NR_LRU_GEN_CAPS; i++) { + bool enabled = caps & BIT(i); + + if (i == LRU_GEN_CORE) + lru_gen_change_state(enabled); + else if (enabled) + static_branch_enable(&lru_gen_caps[i]); + else + static_branch_disable(&lru_gen_caps[i]); + } + + return len; +} + +static struct kobj_attribute lru_gen_enabled_attr = __ATTR( + enabled, 0644, show_enabled, store_enabled +); + +static struct attribute *lru_gen_attrs[] = { + &lru_gen_min_ttl_attr.attr, + &lru_gen_enabled_attr.attr, + NULL +}; + +static struct attribute_group lru_gen_attr_group = { + .name = "lru_gen", + .attrs = lru_gen_attrs, +}; + +/****************************************************************************** + * debugfs interface + ******************************************************************************/ + +static void *lru_gen_seq_start(struct seq_file *m, loff_t *pos) +{ + struct mem_cgroup *memcg; + loff_t nr_to_skip = *pos; + + m->private = kvmalloc(PATH_MAX, GFP_KERNEL); + if (!m->private) + return ERR_PTR(-ENOMEM); + + memcg = mem_cgroup_iter(NULL, NULL, NULL); + do { + int nid; + + for_each_node_state(nid, N_MEMORY) { + if (!nr_to_skip--) + return get_lruvec(memcg, nid); + } + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); + + return NULL; +} + +static void lru_gen_seq_stop(struct seq_file *m, void *v) +{ + if (!IS_ERR_OR_NULL(v)) + mem_cgroup_iter_break(NULL, lruvec_memcg(v)); + + kvfree(m->private); + m->private = NULL; +} + +static void *lru_gen_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + int nid = lruvec_pgdat(v)->node_id; + struct mem_cgroup *memcg = lruvec_memcg(v); + + ++*pos; + + nid = next_memory_node(nid); + if (nid == MAX_NUMNODES) { + memcg = mem_cgroup_iter(NULL, memcg, NULL); + if (!memcg) + return NULL; + + nid = first_memory_node; + } + + return get_lruvec(memcg, nid); +} + +static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec, + unsigned long max_seq, unsigned long *min_seq, + unsigned long seq) +{ + int i; + int type, tier; + int hist = lru_hist_from_seq(seq); + struct lru_gen_struct *lrugen = &lruvec->lrugen; + + for (tier = 0; tier < MAX_NR_TIERS; tier++) { + seq_printf(m, " %10d", tier); + for (type = 0; type < ANON_AND_FILE; type++) { + const char *s = " "; + unsigned long n[3] = {}; + + if (seq == max_seq) { + s = "RT "; + n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]); + n[1] = READ_ONCE(lrugen->avg_total[type][tier]); + } else if (seq == min_seq[type] || NR_HIST_GENS > 1) { + s = "rep"; + n[0] = atomic_long_read(&lrugen->refaulted[hist][type][tier]); + n[1] = atomic_long_read(&lrugen->evicted[hist][type][tier]); + if (tier) + n[2] = READ_ONCE(lrugen->protected[hist][type][tier - 1]); + } + + for (i = 0; i < 3; i++) + seq_printf(m, " %10lu%c", n[i], s[i]); + } + seq_putc(m, '\n'); + } + + seq_puts(m, " "); + for (i = 0; i < NR_MM_STATS; i++) { + const char *s = " "; + unsigned long n = 0; + + if (seq == max_seq && NR_HIST_GENS == 1) { + s = "LOYNFA"; + n = READ_ONCE(lruvec->mm_state.stats[hist][i]); + } else if (seq != max_seq && NR_HIST_GENS > 1) { + s = "loynfa"; + n = READ_ONCE(lruvec->mm_state.stats[hist][i]); + } + + seq_printf(m, " %10lu%c", n, s[i]); + } + seq_putc(m, '\n'); +} + +/* see Documentation/admin-guide/mm/multigen_lru.rst for details */ +static int lru_gen_seq_show(struct seq_file *m, void *v) +{ + unsigned long seq; + bool full = !debugfs_real_fops(m->file)->write; + struct lruvec *lruvec = v; + struct lru_gen_struct *lrugen = &lruvec->lrugen; + int nid = lruvec_pgdat(lruvec)->node_id; + struct mem_cgroup *memcg = lruvec_memcg(lruvec); + DEFINE_MAX_SEQ(lruvec); + DEFINE_MIN_SEQ(lruvec); + + if (nid == first_memory_node) { + const char *path = memcg ? m->private : ""; + +#ifdef CONFIG_MEMCG + if (memcg) + cgroup_path(memcg->css.cgroup, m->private, PATH_MAX); +#endif + seq_printf(m, "memcg %5hu %s\n", mem_cgroup_id(memcg), path); + } + + seq_printf(m, " node %5d\n", nid); + + if (!full) + seq = min_seq[LRU_GEN_ANON]; + else if (max_seq >= MAX_NR_GENS) + seq = max_seq - MAX_NR_GENS + 1; + else + seq = 0; + + for (; seq <= max_seq; seq++) { + int type, zone; + int gen = lru_gen_from_seq(seq); + unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); + + seq_printf(m, " %10lu %10u", seq, jiffies_to_msecs(jiffies - birth)); + + for (type = 0; type < ANON_AND_FILE; type++) { + unsigned long size = 0; + char mark = full && seq < min_seq[type] ? 'x' : ' '; + + for (zone = 0; zone < MAX_NR_ZONES; zone++) + size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); + + seq_printf(m, " %10lu%c", size, mark); + } + + seq_putc(m, '\n'); + + if (full) + lru_gen_seq_show_full(m, lruvec, max_seq, min_seq, seq); + } + + return 0; +} + +static const struct seq_operations lru_gen_seq_ops = { + .start = lru_gen_seq_start, + .stop = lru_gen_seq_stop, + .next = lru_gen_seq_next, + .show = lru_gen_seq_show, +}; + +static int run_aging(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc, + bool can_swap, bool force_scan) +{ + DEFINE_MAX_SEQ(lruvec); + DEFINE_MIN_SEQ(lruvec); + + if (seq < max_seq) + return 0; + + if (seq > max_seq) + return -EINVAL; + + if (!force_scan && min_seq[!can_swap] + MAX_NR_GENS - 1 <= max_seq) + return -ERANGE; + + try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, force_scan); + + return 0; +} + +static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc, + int swappiness, unsigned long nr_to_reclaim) +{ + DEFINE_MAX_SEQ(lruvec); + + if (seq + MIN_NR_GENS > max_seq) + return -EINVAL; + + sc->nr_reclaimed = 0; + + while (!signal_pending(current)) { + DEFINE_MIN_SEQ(lruvec); + + if (seq < min_seq[!swappiness]) + return 0; + + if (sc->nr_reclaimed >= nr_to_reclaim) + return 0; + + if (!evict_folios(lruvec, sc, swappiness, NULL)) + return 0; + + cond_resched(); + } + + return -EINTR; +} + +static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq, + struct scan_control *sc, int swappiness, unsigned long opt) +{ + struct lruvec *lruvec; + int err = -EINVAL; + struct mem_cgroup *memcg = NULL; + + if (nid < 0 || nid >= MAX_NUMNODES || !node_state(nid, N_MEMORY)) + return -EINVAL; + + if (!mem_cgroup_disabled()) { + rcu_read_lock(); + memcg = mem_cgroup_from_id(memcg_id); +#ifdef CONFIG_MEMCG + if (memcg && !css_tryget(&memcg->css)) + memcg = NULL; +#endif + rcu_read_unlock(); + + if (!memcg) + return -EINVAL; + } + + if (memcg_id != mem_cgroup_id(memcg)) + goto done; + + lruvec = get_lruvec(memcg, nid); + + if (swappiness < 0) + swappiness = get_swappiness(lruvec, sc); + else if (swappiness > 200) + goto done; + + switch (cmd) { + case '+': + err = run_aging(lruvec, seq, sc, swappiness, opt); + break; + case '-': + err = run_eviction(lruvec, seq, sc, swappiness, opt); + break; + } +done: + mem_cgroup_put(memcg); + + return err; +} + +/* see Documentation/admin-guide/mm/multigen_lru.rst for details */ +static ssize_t lru_gen_seq_write(struct file *file, const char __user *src, + size_t len, loff_t *pos) +{ + void *buf; + char *cur, *next; + unsigned int flags; + struct blk_plug plug; + int err = -EINVAL; + struct scan_control sc = { + .may_writepage = true, + .may_unmap = true, + .may_swap = true, + .reclaim_idx = MAX_NR_ZONES - 1, + .gfp_mask = GFP_KERNEL, + }; + + buf = kvmalloc(len + 1, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + if (copy_from_user(buf, src, len)) { + kvfree(buf); + return -EFAULT; + } + + set_task_reclaim_state(current, &sc.reclaim_state); + flags = memalloc_noreclaim_save(); + blk_start_plug(&plug); + if (!set_mm_walk(NULL)) { + err = -ENOMEM; + goto done; + } + + next = buf; + next[len] = '\0'; + + while ((cur = strsep(&next, ",;\n"))) { + int n; + int end; + char cmd; + unsigned int memcg_id; + unsigned int nid; + unsigned long seq; + unsigned int swappiness = -1; + unsigned long opt = -1; + + cur = skip_spaces(cur); + if (!*cur) + continue; + + n = sscanf(cur, "%c %u %u %lu %n %u %n %lu %n", &cmd, &memcg_id, &nid, + &seq, &end, &swappiness, &end, &opt, &end); + if (n < 4 || cur[end]) { + err = -EINVAL; + break; + } + + err = run_cmd(cmd, memcg_id, nid, seq, &sc, swappiness, opt); + if (err) + break; + } +done: + clear_mm_walk(); + blk_finish_plug(&plug); + memalloc_noreclaim_restore(flags); + set_task_reclaim_state(current, NULL); + + kvfree(buf); + + return err ? : len; +} + +static int lru_gen_seq_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &lru_gen_seq_ops); +} + +static const struct file_operations lru_gen_rw_fops = { + .open = lru_gen_seq_open, + .read = seq_read, + .write = lru_gen_seq_write, + .llseek = seq_lseek, + .release = seq_release, +}; + +static const struct file_operations lru_gen_ro_fops = { + .open = lru_gen_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +/****************************************************************************** + * initialization + ******************************************************************************/ + +void lru_gen_init_lruvec(struct lruvec *lruvec) +{ + int i; + int gen, type, zone; + struct lru_gen_struct *lrugen = &lruvec->lrugen; + + lrugen->max_seq = MIN_NR_GENS + 1; + lrugen->enabled = lru_gen_enabled(); + + for (i = 0; i <= MIN_NR_GENS + 1; i++) + lrugen->timestamps[i] = jiffies; + + for_each_gen_type_zone(gen, type, zone) + INIT_LIST_HEAD(&lrugen->lists[gen][type][zone]); + + lruvec->mm_state.seq = MIN_NR_GENS; + init_waitqueue_head(&lruvec->mm_state.wait); +} + +#ifdef CONFIG_MEMCG +void lru_gen_init_memcg(struct mem_cgroup *memcg) +{ + INIT_LIST_HEAD(&memcg->mm_list.fifo); + spin_lock_init(&memcg->mm_list.lock); +} + +void lru_gen_exit_memcg(struct mem_cgroup *memcg) +{ + int i; + int nid; + + for_each_node(nid) { + struct lruvec *lruvec = get_lruvec(memcg, nid); + + VM_WARN_ON_ONCE(memchr_inv(lruvec->lrugen.nr_pages, 0, + sizeof(lruvec->lrugen.nr_pages))); + + for (i = 0; i < NR_BLOOM_FILTERS; i++) { + bitmap_free(lruvec->mm_state.filters[i]); + lruvec->mm_state.filters[i] = NULL; + } + } +} +#endif + +static int __init init_lru_gen(void) +{ + BUILD_BUG_ON(MIN_NR_GENS + 1 >= MAX_NR_GENS); + BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS); + + if (sysfs_create_group(mm_kobj, &lru_gen_attr_group)) + pr_err("lru_gen: failed to create sysfs group\n"); + + debugfs_create_file("lru_gen", 0644, NULL, NULL, &lru_gen_rw_fops); + debugfs_create_file("lru_gen_full", 0444, NULL, NULL, &lru_gen_ro_fops); + + return 0; +}; +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) { unsigned long nr[NR_LRU_LISTS]; @@ -2452,6 +5847,11 @@ 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 */ @@ -2550,7 +5950,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ - if (total_swap_pages && inactive_is_low(lruvec, LRU_INACTIVE_ANON)) + if (can_age_anon_pages(lruvec_pgdat(lruvec), sc) && + inactive_is_low(lruvec, LRU_INACTIVE_ANON)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } @@ -2570,7 +5971,7 @@ static bool in_reclaim_compaction(struct scan_control *sc) * Reclaim/compaction is used for high-order allocation requests. It reclaims * order-0 pages before compacting the zone. should_continue_reclaim() returns * true if more pages should be reclaimed such that when the page allocator - * calls try_to_compact_zone() that it will have enough free pages to succeed. + * calls try_to_compact_pages() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ static inline bool should_continue_reclaim(struct pglist_data *pgdat, @@ -2620,7 +6021,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat, */ pages_for_compaction = compact_gap(sc->order); inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); - if (get_nr_swap_pages() > 0) + if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); return inactive_lru_pages > pages_for_compaction; @@ -2637,14 +6038,23 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) unsigned long reclaimed; unsigned long scanned; - switch (mem_cgroup_protected(target_memcg, memcg)) { - case MEMCG_PROT_MIN: + /* + * This loop can become CPU-bound when target memcgs + * aren't eligible for reclaim - either because they + * don't have any reclaimable pages, or because their + * memory is explicitly protected. Avoid soft lockups. + */ + cond_resched(); + + mem_cgroup_calculate_protection(target_memcg, memcg); + + if (mem_cgroup_below_min(memcg)) { /* * Hard protection. * If there is no reclaimable memory, OOM. */ continue; - case MEMCG_PROT_LOW: + } else if (mem_cgroup_below_low(memcg)) { /* * Soft protection. * Respect the protection only as long as @@ -2656,16 +6066,6 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) continue; } memcg_memory_event(memcg, MEMCG_LOW); - break; - case MEMCG_PROT_NONE: - /* - * All protection thresholds breached. We may - * still choose to vary the scan pressure - * applied based on by how much the cgroup in - * question has exceeded its protection - * thresholds (see get_scan_count). - */ - break; } reclaimed = sc->nr_reclaimed; @@ -2677,9 +6077,10 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) sc->priority); /* Record the group's reclaim efficiency */ - vmpressure(sc->gfp_mask, memcg, false, - sc->nr_scanned - scanned, - sc->nr_reclaimed - reclaimed); + if (!sc->proactive) + vmpressure(sc->gfp_mask, memcg, false, + sc->nr_scanned - scanned, + sc->nr_reclaimed - reclaimed); } while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL))); } @@ -2690,7 +6091,6 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) unsigned long nr_reclaimed, nr_scanned; struct lruvec *target_lruvec; bool reclaimable = false; - unsigned long file; target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); @@ -2700,82 +6100,7 @@ again: nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; - /* - * Target desirable inactive:active list ratios for the anon - * and file LRU lists. - */ - if (!sc->force_deactivate) { - unsigned long refaults; - - if (inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) - sc->may_deactivate |= DEACTIVATE_ANON; - else - sc->may_deactivate &= ~DEACTIVATE_ANON; - - /* - * 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); - if (refaults != target_lruvec->refaults || - 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->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; - } + prepare_scan_count(pgdat, sc); shrink_node_memcgs(pgdat, sc); @@ -2785,9 +6110,10 @@ again: } /* Record the subtree's reclaim efficiency */ - vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, - sc->nr_scanned - nr_scanned, - sc->nr_reclaimed - nr_reclaimed); + if (!sc->proactive) + vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, + sc->nr_scanned - nr_scanned, + sc->nr_reclaimed - nr_reclaimed); if (sc->nr_reclaimed - nr_reclaimed) reclaimable = true; @@ -2818,22 +6144,22 @@ again: set_bit(PGDAT_DIRTY, &pgdat->flags); /* - * If kswapd scans pages marked marked for immediate + * If kswapd scans pages marked for immediate * reclaim and under writeback (nr_immediate), it * implies that pages are cycling through the LRU - * faster than they are written so also forcibly stall. + * faster than they are written so forcibly stall + * until some pages complete writeback. */ if (sc->nr.immediate) - congestion_wait(BLK_RW_ASYNC, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } /* - * Tag a node/memcg as congested if all the dirty pages - * scanned were backed by a congested BDI and - * wait_iff_congested will stall. + * Tag a node/memcg as congested if all the dirty pages were marked + * for writeback and immediate reclaim (counted in nr.congested). * * Legacy memcg will stall in page writeback so avoid forcibly - * stalling in wait_iff_congested(). + * stalling in reclaim_throttle(). */ if ((current_is_kswapd() || (cgroup_reclaim(sc) && writeback_throttling_sane(sc))) && @@ -2841,15 +6167,15 @@ again: set_bit(LRUVEC_CONGESTED, &target_lruvec->flags); /* - * Stall direct reclaim for IO completions if underlying BDIs - * and node is congested. Allow kswapd to continue until it + * Stall direct reclaim for IO completions if the lruvec is + * node is congested. Allow kswapd to continue until it * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) - wait_iff_congested(BLK_RW_ASYNC, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED); if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc)) @@ -2897,6 +6223,36 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); } +static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc) +{ + /* + * If reclaim is making progress greater than 12% efficiency then + * wake all the NOPROGRESS throttled tasks. + */ + if (sc->nr_reclaimed > (sc->nr_scanned >> 3)) { + wait_queue_head_t *wqh; + + wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS]; + if (waitqueue_active(wqh)) + wake_up(wqh); + + return; + } + + /* + * Do not throttle kswapd or cgroup reclaim on NOPROGRESS as it will + * throttle on VMSCAN_THROTTLE_WRITEBACK if there are too many pages + * under writeback and marked for immediate reclaim at the tail of the + * LRU. + */ + if (current_is_kswapd() || cgroup_reclaim(sc)) + return; + + /* Throttle if making no progress at high prioities. */ + if (sc->priority == 1 && !sc->nr_reclaimed) + reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS); +} + /* * This is the direct reclaim path, for page-allocating processes. We only * try to reclaim pages from zones which will satisfy the caller's allocation @@ -2913,6 +6269,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) unsigned long nr_soft_scanned; gfp_t orig_mask; pg_data_t *last_pgdat = NULL; + pg_data_t *first_pgdat = NULL; /* * If the number of buffer_heads in the machine exceeds the maximum @@ -2976,6 +6333,9 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) /* need some check for avoid more shrink_zone() */ } + if (!first_pgdat) + first_pgdat = zone->zone_pgdat; + /* See comment about same check for global reclaim above */ if (zone->zone_pgdat == last_pgdat) continue; @@ -2983,6 +6343,9 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) shrink_node(zone->zone_pgdat, sc); } + if (first_pgdat) + consider_reclaim_throttle(first_pgdat, sc); + /* * Restore to original mask to avoid the impact on the caller if we * promoted it to __GFP_HIGHMEM. @@ -2995,9 +6358,14 @@ 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); - target_lruvec->refaults = refaults; + refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); + target_lruvec->refaults[WORKINGSET_ANON] = refaults; + refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); + target_lruvec->refaults[WORKINGSET_FILE] = refaults; } /* @@ -3030,8 +6398,9 @@ retry: __count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1); do { - vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, - sc->priority); + if (!sc->proactive) + vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, + sc->priority); sc->nr_scanned = 0; shrink_zones(zonelist, sc); @@ -3096,7 +6465,6 @@ retry: if (sc->memcg_low_skipped) { sc->priority = initial_priority; sc->force_deactivate = 0; - sc->skipped_deactivate = 0; sc->memcg_low_reclaim = 1; sc->memcg_low_skipped = 0; goto retry; @@ -3136,8 +6504,9 @@ static bool allow_direct_reclaim(pg_data_t *pgdat) /* kswapd must be awake if processes are being throttled */ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { - pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx, - (enum zone_type)ZONE_NORMAL); + if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL) + WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL); + wake_up_interruptible(&pgdat->kswapd_wait); } @@ -3218,18 +6587,14 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, * blocked waiting on the same lock. Instead, throttle for up to a * second before continuing. */ - if (!(gfp_mask & __GFP_FS)) { + if (!(gfp_mask & __GFP_FS)) wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat), HZ); + else + /* Throttle until kswapd wakes the process */ + wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, + allow_direct_reclaim(pgdat)); - goto check_pending; - } - - /* Throttle until kswapd wakes the process */ - wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, - allow_direct_reclaim(pgdat)); - -check_pending: if (fatal_signal_pending(current)) return true; @@ -3325,10 +6690,9 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - bool may_swap) + unsigned int reclaim_options) { unsigned long nr_reclaimed; - unsigned long pflags; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), @@ -3339,7 +6703,8 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, - .may_swap = may_swap, + .may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP), + .proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE), }; /* * Traverse the ZONELIST_FALLBACK zonelist of the current node to put @@ -3349,17 +6714,12 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); set_task_reclaim_state(current, &sc.reclaim_state); - trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); - - psi_memstall_enter(&pflags); noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); memalloc_noreclaim_restore(noreclaim_flag); - psi_memstall_leave(&pflags); - trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); @@ -3367,13 +6727,17 @@ 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 (!total_swap_pages) + if (lru_gen_enabled()) { + lru_gen_age_node(pgdat, sc); + return; + } + + if (!can_age_anon_pages(pgdat, sc)) return; lruvec = mem_cgroup_lruvec(NULL, pgdat); @@ -3389,7 +6753,7 @@ static void age_active_anon(struct pglist_data *pgdat, } while (memcg); } -static bool pgdat_watermark_boosted(pg_data_t *pgdat, int classzone_idx) +static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx) { int i; struct zone *zone; @@ -3397,11 +6761,11 @@ static bool pgdat_watermark_boosted(pg_data_t *pgdat, int classzone_idx) /* * Check for watermark boosts top-down as the higher zones * are more likely to be boosted. Both watermarks and boosts - * should not be checked at the time time as reclaim would + * should not be checked at the same time as reclaim would * start prematurely when there is no boosting and a lower * zone is balanced. */ - for (i = classzone_idx; i >= 0; i--) { + for (i = highest_zoneidx; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; @@ -3415,9 +6779,9 @@ static bool pgdat_watermark_boosted(pg_data_t *pgdat, int classzone_idx) /* * Returns true if there is an eligible zone balanced for the request order - * and classzone_idx + * and highest_zoneidx */ -static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) +static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long mark = -1; @@ -3427,19 +6791,22 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) * Check watermarks bottom-up as lower zones are more likely to * meet watermarks. */ - for (i = 0; i <= classzone_idx; i++) { + for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; - mark = high_wmark_pages(zone); - if (zone_watermark_ok_safe(zone, order, mark, classzone_idx)) + if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) + mark = wmark_pages(zone, WMARK_PROMO); + else + mark = high_wmark_pages(zone); + if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx)) return true; } /* - * If a node has no populated zone within classzone_idx, it does not + * If a node has no managed zone within highest_zoneidx, it does not * need balancing by definition. This can happen if a zone-restricted * allocation tries to wake a remote kswapd. */ @@ -3465,7 +6832,8 @@ static void clear_pgdat_congested(pg_data_t *pgdat) * * Returns true if kswapd is ready to sleep */ -static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx) +static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, + int highest_zoneidx) { /* * The throttled processes are normally woken up in balance_pgdat() as @@ -3487,7 +6855,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx) if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; - if (pgdat_balanced(pgdat, order, classzone_idx)) { + if (pgdat_balanced(pgdat, order, highest_zoneidx)) { clear_pgdat_congested(pgdat); return true; } @@ -3538,6 +6906,38 @@ static bool kswapd_shrink_node(pg_data_t *pgdat, return sc->nr_scanned >= sc->nr_to_reclaim; } +/* Page allocator PCP high watermark is lowered if reclaim is active. */ +static inline void +update_reclaim_active(pg_data_t *pgdat, int highest_zoneidx, bool active) +{ + int i; + struct zone *zone; + + for (i = 0; i <= highest_zoneidx; i++) { + zone = pgdat->node_zones + i; + + if (!managed_zone(zone)) + continue; + + if (active) + set_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); + else + clear_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); + } +} + +static inline void +set_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) +{ + update_reclaim_active(pgdat, highest_zoneidx, true); +} + +static inline void +clear_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) +{ + update_reclaim_active(pgdat, highest_zoneidx, false); +} + /* * For kswapd, balance_pgdat() will reclaim pages across a node from zones * that are eligible for use by the caller until at least one zone is @@ -3551,7 +6951,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat, * or lower is eligible for reclaim until at least one usable zone is * balanced. */ -static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) +static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long nr_soft_reclaimed; @@ -3569,7 +6969,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) set_task_reclaim_state(current, &sc.reclaim_state); psi_memstall_enter(&pflags); - __fs_reclaim_acquire(); + __fs_reclaim_acquire(_THIS_IP_); count_vm_event(PAGEOUTRUN); @@ -3579,7 +6979,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) * stall or direct reclaim until kswapd is finished. */ nr_boost_reclaim = 0; - for (i = 0; i <= classzone_idx; i++) { + for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; @@ -3590,6 +6990,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) boosted = nr_boost_reclaim; restart: + set_reclaim_active(pgdat, highest_zoneidx); sc.priority = DEF_PRIORITY; do { unsigned long nr_reclaimed = sc.nr_reclaimed; @@ -3597,7 +6998,7 @@ restart: bool balanced; bool ret; - sc.reclaim_idx = classzone_idx; + sc.reclaim_idx = highest_zoneidx; /* * If the number of buffer_heads exceeds the maximum allowed @@ -3627,7 +7028,7 @@ restart: * on the grounds that the normal reclaim should be enough to * re-evaluate if boosting is required when kswapd next wakes. */ - balanced = pgdat_balanced(pgdat, sc.order, classzone_idx); + balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx); if (!balanced && nr_boost_reclaim) { nr_boost_reclaim = 0; goto restart; @@ -3655,12 +7056,11 @@ 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 @@ -3694,9 +7094,9 @@ restart: wake_up_all(&pgdat->pfmemalloc_wait); /* Check if kswapd should be suspending */ - __fs_reclaim_release(); + __fs_reclaim_release(_THIS_IP_); ret = try_to_freeze(); - __fs_reclaim_acquire(); + __fs_reclaim_acquire(_THIS_IP_); if (ret || kthread_should_stop()) break; @@ -3723,11 +7123,13 @@ restart: pgdat->kswapd_failures++; out: + clear_reclaim_active(pgdat, highest_zoneidx); + /* If reclaim was boosted, account for the reclaim done in this pass */ if (boosted) { unsigned long flags; - for (i = 0; i <= classzone_idx; i++) { + for (i = 0; i <= highest_zoneidx; i++) { if (!zone_boosts[i]) continue; @@ -3742,11 +7144,11 @@ out: * As there is now likely space, wakeup kcompact to defragment * pageblocks. */ - wakeup_kcompactd(pgdat, pageblock_order, classzone_idx); + wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx); } snapshot_refaults(NULL, pgdat); - __fs_reclaim_release(); + __fs_reclaim_release(_THIS_IP_); psi_memstall_leave(&pflags); set_task_reclaim_state(current, NULL); @@ -3760,22 +7162,22 @@ out: } /* - * The pgdat->kswapd_classzone_idx is used to pass the highest zone index to be - * reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is not - * a valid index then either kswapd runs for first time or kswapd couldn't sleep - * after previous reclaim attempt (node is still unbalanced). In that case - * return the zone index of the previous kswapd reclaim cycle. + * The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to + * be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is + * not a valid index then either kswapd runs for first time or kswapd couldn't + * sleep after previous reclaim attempt (node is still unbalanced). In that + * case return the zone index of the previous kswapd reclaim cycle. */ -static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat, - enum zone_type prev_classzone_idx) +static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat, + enum zone_type prev_highest_zoneidx) { - if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES) - return prev_classzone_idx; - return pgdat->kswapd_classzone_idx; + enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); + + return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, - unsigned int classzone_idx) + unsigned int highest_zoneidx) { long remaining = 0; DEFINE_WAIT(wait); @@ -3792,7 +7194,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o * eligible zone balanced that it's also unlikely that compaction will * succeed. */ - if (prepare_kswapd_sleep(pgdat, reclaim_order, classzone_idx)) { + if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { /* * Compaction records what page blocks it recently failed to * isolate pages from and skips them in the future scanning. @@ -3805,18 +7207,22 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o * We have freed the memory, now we should compact it to make * allocation of the requested order possible. */ - wakeup_kcompactd(pgdat, alloc_order, classzone_idx); + wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx); remaining = schedule_timeout(HZ/10); /* - * If woken prematurely then reset kswapd_classzone_idx and + * If woken prematurely then reset kswapd_highest_zoneidx and * order. The values will either be from a wakeup request or * the previous request that slept prematurely. */ if (remaining) { - pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx); - pgdat->kswapd_order = max(pgdat->kswapd_order, reclaim_order); + WRITE_ONCE(pgdat->kswapd_highest_zoneidx, + kswapd_highest_zoneidx(pgdat, + highest_zoneidx)); + + if (READ_ONCE(pgdat->kswapd_order) < reclaim_order) + WRITE_ONCE(pgdat->kswapd_order, reclaim_order); } finish_wait(&pgdat->kswapd_wait, &wait); @@ -3828,7 +7234,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o * go fully to sleep until explicitly woken up. */ if (!remaining && - prepare_kswapd_sleep(pgdat, reclaim_order, classzone_idx)) { + prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); /* @@ -3870,8 +7276,8 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o static int kswapd(void *p) { unsigned int alloc_order, reclaim_order; - unsigned int classzone_idx = MAX_NR_ZONES - 1; - pg_data_t *pgdat = (pg_data_t*)p; + unsigned int highest_zoneidx = MAX_NR_ZONES - 1; + pg_data_t *pgdat = (pg_data_t *)p; struct task_struct *tsk = current; const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); @@ -3890,26 +7296,29 @@ static int kswapd(void *p) * us from recursively trying to free more memory as we're * trying to free the first piece of memory in the first place). */ - tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; + tsk->flags |= PF_MEMALLOC | PF_KSWAPD; set_freezable(); - pgdat->kswapd_order = 0; - pgdat->kswapd_classzone_idx = MAX_NR_ZONES; + WRITE_ONCE(pgdat->kswapd_order, 0); + WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); + atomic_set(&pgdat->nr_writeback_throttled, 0); for ( ; ; ) { bool ret; - alloc_order = reclaim_order = pgdat->kswapd_order; - classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx); + alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); + highest_zoneidx = kswapd_highest_zoneidx(pgdat, + highest_zoneidx); kswapd_try_sleep: kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, - classzone_idx); + highest_zoneidx); - /* Read the new order and classzone_idx */ - alloc_order = reclaim_order = pgdat->kswapd_order; - classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx); - pgdat->kswapd_order = 0; - pgdat->kswapd_classzone_idx = MAX_NR_ZONES; + /* Read the new order and highest_zoneidx */ + alloc_order = READ_ONCE(pgdat->kswapd_order); + highest_zoneidx = kswapd_highest_zoneidx(pgdat, + highest_zoneidx); + WRITE_ONCE(pgdat->kswapd_order, 0); + WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); ret = try_to_freeze(); if (kthread_should_stop()) @@ -3930,14 +7339,15 @@ kswapd_try_sleep: * but kcompactd is woken to compact for the original * request (alloc_order). */ - trace_mm_vmscan_kswapd_wake(pgdat->node_id, classzone_idx, + trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx, alloc_order); - reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx); + reclaim_order = balance_pgdat(pgdat, alloc_order, + highest_zoneidx); if (reclaim_order < alloc_order) goto kswapd_try_sleep; } - tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD); + tsk->flags &= ~(PF_MEMALLOC | PF_KSWAPD); return 0; } @@ -3950,30 +7360,33 @@ kswapd_try_sleep: * needed. */ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, - enum zone_type classzone_idx) + enum zone_type highest_zoneidx) { pg_data_t *pgdat; + enum zone_type curr_idx; if (!managed_zone(zone)) return; if (!cpuset_zone_allowed(zone, gfp_flags)) return; + pgdat = zone->zone_pgdat; + curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); + + if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx) + WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx); + + if (READ_ONCE(pgdat->kswapd_order) < order) + WRITE_ONCE(pgdat->kswapd_order, order); - if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES) - pgdat->kswapd_classzone_idx = classzone_idx; - else - pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, - classzone_idx); - pgdat->kswapd_order = max(pgdat->kswapd_order, order); if (!waitqueue_active(&pgdat->kswapd_wait)) return; /* Hopeless node, leave it to direct reclaim if possible */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || - (pgdat_balanced(pgdat, order, classzone_idx) && - !pgdat_watermark_boosted(pgdat, classzone_idx))) { + (pgdat_balanced(pgdat, order, highest_zoneidx) && + !pgdat_watermark_boosted(pgdat, highest_zoneidx))) { /* * There may be plenty of free memory available, but it's too * fragmented for high-order allocations. Wake up kcompactd @@ -3982,11 +7395,11 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, * ratelimit its work. */ if (!(gfp_flags & __GFP_DIRECT_RECLAIM)) - wakeup_kcompactd(pgdat, order, classzone_idx); + wakeup_kcompactd(pgdat, order, highest_zoneidx); return; } - trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, classzone_idx, order, + trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order, gfp_flags); wake_up_interruptible(&pgdat->kswapd_wait); } @@ -4030,75 +7443,51 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) } #endif /* CONFIG_HIBERNATION */ -/* It's optimal to keep kswapds on the same CPUs as their memory, but - not required for correctness. So if the last cpu in a node goes - away, we get changed to run anywhere: as the first one comes back, - restore their cpu bindings. */ -static int kswapd_cpu_online(unsigned int cpu) -{ - int nid; - - for_each_node_state(nid, N_MEMORY) { - pg_data_t *pgdat = NODE_DATA(nid); - const struct cpumask *mask; - - mask = cpumask_of_node(pgdat->node_id); - - if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids) - /* One of our CPUs online: restore mask */ - set_cpus_allowed_ptr(pgdat->kswapd, mask); - } - return 0; -} - /* * This kswapd start function will be called by init and node-hot-add. - * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added. */ -int kswapd_run(int nid) +void kswapd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); - int ret = 0; - - if (pgdat->kswapd) - return 0; - pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); - if (IS_ERR(pgdat->kswapd)) { - /* failure at boot is fatal */ - BUG_ON(system_state < SYSTEM_RUNNING); - pr_err("Failed to start kswapd on node %d\n", nid); - ret = PTR_ERR(pgdat->kswapd); - pgdat->kswapd = NULL; + pgdat_kswapd_lock(pgdat); + if (!pgdat->kswapd) { + pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); + if (IS_ERR(pgdat->kswapd)) { + /* failure at boot is fatal */ + BUG_ON(system_state < SYSTEM_RUNNING); + pr_err("Failed to start kswapd on node %d\n", nid); + pgdat->kswapd = NULL; + } } - return ret; + pgdat_kswapd_unlock(pgdat); } /* * Called by memory hotplug when all memory in a node is offlined. Caller must - * hold mem_hotplug_begin/end(). + * be holding mem_hotplug_begin/done(). */ void kswapd_stop(int nid) { - struct task_struct *kswapd = NODE_DATA(nid)->kswapd; + pg_data_t *pgdat = NODE_DATA(nid); + struct task_struct *kswapd; + pgdat_kswapd_lock(pgdat); + kswapd = pgdat->kswapd; if (kswapd) { kthread_stop(kswapd); - NODE_DATA(nid)->kswapd = NULL; + pgdat->kswapd = NULL; } + pgdat_kswapd_unlock(pgdat); } static int __init kswapd_init(void) { - int nid, ret; + int nid; swap_setup(); for_each_node_state(nid, N_MEMORY) kswapd_run(nid); - ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, - "mm/vmscan:online", kswapd_cpu_online, - NULL); - WARN_ON(ret < 0); return 0; } @@ -4113,9 +7502,6 @@ module_init(kswapd_init) */ int node_reclaim_mode __read_mostly; -#define RECLAIM_WRITE (1<<0) /* Writeout pages during reclaim */ -#define RECLAIM_UNMAP (1<<1) /* Unmap pages during reclaim */ - /* * Priority for NODE_RECLAIM. This determines the fraction of pages * of a node considered for each zone_reclaim. 4 scans 1/16th of @@ -4196,22 +7582,22 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in .may_swap = 1, .reclaim_idx = gfp_zone(gfp_mask), }; + unsigned long pflags; trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order, sc.gfp_mask); cond_resched(); + psi_memstall_enter(&pflags); fs_reclaim_acquire(sc.gfp_mask); /* * We need to be able to allocate from the reserves for RECLAIM_UNMAP - * and we also need to be able to write out pages for RECLAIM_WRITE - * and RECLAIM_UNMAP. */ noreclaim_flag = memalloc_noreclaim_save(); - p->flags |= PF_SWAPWRITE; set_task_reclaim_state(p, &sc.reclaim_state); - if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) { + if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages || + node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) > pgdat->min_slab_pages) { /* * Free memory by calling shrink node with increasing * priorities until we have enough memory freed. @@ -4222,9 +7608,9 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in } set_task_reclaim_state(p, NULL); - current->flags &= ~PF_SWAPWRITE; memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); + psi_memstall_leave(&pflags); trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); @@ -4246,7 +7632,8 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) * unmapped file backed pages. */ if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages && - node_page_state(pgdat, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages) + node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <= + pgdat->min_slab_pages) return NODE_RECLAIM_FULL; /* @@ -4277,77 +7664,65 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) } #endif -/* - * page_evictable - test whether a page is evictable - * @page: the page to test - * - * Test whether page is evictable--i.e., should be placed on active/inactive - * lists vs unevictable list. - * - * Reasons page might not be evictable: - * (1) page's mapping marked unevictable - * (2) page is part of an mlocked VMA - * - */ -int page_evictable(struct page *page) +void check_move_unevictable_pages(struct pagevec *pvec) { - int ret; + struct folio_batch fbatch; + unsigned i; - /* Prevent address_space of inode and swap cache from being freed */ - rcu_read_lock(); - ret = !mapping_unevictable(page_mapping(page)) && !PageMlocked(page); - rcu_read_unlock(); - return ret; + folio_batch_init(&fbatch); + for (i = 0; i < pvec->nr; i++) { + struct page *page = pvec->pages[i]; + + if (PageTransTail(page)) + continue; + folio_batch_add(&fbatch, page_folio(page)); + } + check_move_unevictable_folios(&fbatch); } +EXPORT_SYMBOL_GPL(check_move_unevictable_pages); /** - * check_move_unevictable_pages - check pages for evictability and move to - * appropriate zone lru list - * @pvec: pagevec with lru pages to check + * check_move_unevictable_folios - Move evictable folios to appropriate zone + * lru list + * @fbatch: Batch of lru folios to check. * - * Checks pages for evictability, if an evictable page is in the unevictable + * Checks folios for evictability, if an evictable folio is in the unevictable * lru list, moves it to the appropriate evictable lru list. This function - * should be only used for lru pages. + * should be only used for lru folios. */ -void check_move_unevictable_pages(struct pagevec *pvec) +void check_move_unevictable_folios(struct folio_batch *fbatch) { - struct lruvec *lruvec; - struct pglist_data *pgdat = NULL; + struct lruvec *lruvec = NULL; int pgscanned = 0; int pgrescued = 0; int i; - for (i = 0; i < pvec->nr; i++) { - struct page *page = pvec->pages[i]; - struct pglist_data *pagepgdat = page_pgdat(page); - - pgscanned++; - if (pagepgdat != pgdat) { - if (pgdat) - spin_unlock_irq(&pgdat->lru_lock); - pgdat = pagepgdat; - spin_lock_irq(&pgdat->lru_lock); - } - lruvec = mem_cgroup_page_lruvec(page, pgdat); + for (i = 0; i < fbatch->nr; i++) { + struct folio *folio = fbatch->folios[i]; + int nr_pages = folio_nr_pages(folio); - if (!PageLRU(page) || !PageUnevictable(page)) - continue; + pgscanned += nr_pages; - if (page_evictable(page)) { - enum lru_list lru = page_lru_base_type(page); + /* block memcg migration while the folio moves between lrus */ + if (!folio_test_clear_lru(folio)) + continue; - VM_BUG_ON_PAGE(PageActive(page), page); - ClearPageUnevictable(page); - del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE); - add_page_to_lru_list(page, lruvec, lru); - pgrescued++; + lruvec = folio_lruvec_relock_irq(folio, lruvec); + if (folio_evictable(folio) && folio_test_unevictable(folio)) { + lruvec_del_folio(lruvec, folio); + folio_clear_unevictable(folio); + lruvec_add_folio(lruvec, folio); + pgrescued += nr_pages; } + folio_set_lru(folio); } - if (pgdat) { + if (lruvec) { __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); - spin_unlock_irq(&pgdat->lru_lock); + unlock_page_lruvec_irq(lruvec); + } else if (pgscanned) { + count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); } } -EXPORT_SYMBOL_GPL(check_move_unevictable_pages); +EXPORT_SYMBOL_GPL(check_move_unevictable_folios); |