diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index ebfc4dd30d23c1b8dba10555e02a6a16243a6646..e971097491e32d1e08dc5ff0e5f01ed8d3aefef5 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -125,6 +125,19 @@ static inline int lru_gen_from_seq(unsigned long seq) return seq % MAX_NR_GENS; } +static inline int lru_hist_from_seq(unsigned long seq) +{ + return seq % NR_HIST_GENS; +} + +static inline int lru_tier_from_refs(int refs) +{ + VM_BUG_ON(refs > BIT(LRU_REFS_WIDTH)); + + /* see the comment on MAX_NR_TIERS */ + return order_base_2(refs + 1); +} + static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen) { unsigned long max_seq = lruvec->lrugen.max_seq; @@ -170,6 +183,15 @@ static inline void lru_gen_update_size(struct lruvec *lruvec, struct page *page, __update_lru_size(lruvec, lru, zone, -delta); return; } + + /* promotion */ + if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) { + __update_lru_size(lruvec, lru, zone, -delta); + __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta); + } + + /* demotion requires isolation, e.g., lru_deactivate_fn() */ + VM_BUG_ON(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); } static inline bool lru_gen_add_page(struct lruvec *lruvec, struct page *page, bool reclaiming) @@ -234,6 +256,8 @@ static inline bool lru_gen_del_page(struct lruvec *lruvec, struct page *page, bo gen = ((new_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; new_flags &= ~LRU_GEN_MASK; + if (!(new_flags & BIT(PG_referenced))) + new_flags &= ~(LRU_REFS_MASK | LRU_REFS_FLAGS); /* for shrink_page_list() */ if (reclaiming) new_flags &= ~(BIT(PG_referenced) | BIT(PG_reclaim)); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index d9ffe86dbde99748f9d0f11a07bd7adc5eea0e52..2b5e5eef7b801b418ebec93d37f981348f4a54f8 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -309,12 +309,34 @@ enum lruvec_flags { #define MIN_NR_GENS 2U #define MAX_NR_GENS 4U +/* + * Each generation is divided into multiple tiers. Tiers represent different + * ranges of numbers of accesses through file descriptors. A page accessed N + * times through file descriptors is in tier order_base_2(N). A page in the + * first tier (N=0,1) is marked by PG_referenced unless it was faulted in + * though page tables or read ahead. A page in any other tier (N>1) is marked + * by PG_referenced and PG_workingset. + * + * In contrast to moving across generations which requires the LRU lock, moving + * across tiers only requires operations on page->flags and therefore has a + * negligible cost in the buffered access path. In the eviction path, + * comparisons of refaulted/(evicted+protected) from the first tier and the + * rest infer whether pages accessed multiple times through file descriptors + * are statistically hot and thus worth protecting. + * + * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice of the + * categories of the active/inactive LRU when keeping track of accesses through + * file descriptors. It requires MAX_NR_TIERS-2 additional bits in page->flags. + */ +#define MAX_NR_TIERS 4U + #ifndef __GENERATING_BOUNDS_H struct lruvec; #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) +#define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset)) #ifdef CONFIG_LRU_GEN @@ -323,6 +345,16 @@ enum { LRU_GEN_FILE, }; +#define MIN_LRU_BATCH BITS_PER_LONG +#define MAX_LRU_BATCH (MIN_LRU_BATCH * 128) + +/* whether to keep historical stats from evicted generations */ +#ifdef CONFIG_LRU_GEN_STATS +#define NR_HIST_GENS MAX_NR_GENS +#else +#define NR_HIST_GENS 1U +#endif + /* * The youngest generation number is stored in max_seq for both anon and file * types as they are aged on an equal footing. The oldest generation numbers are @@ -342,6 +374,15 @@ struct lru_gen_struct { struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the sizes of the above lists */ unsigned long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; + /* the exponential moving average of refaulted */ + unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS]; + /* the exponential moving average of evicted+protected */ + unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS]; + /* the first tier doesn't need protection, hence the minus one */ + unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1]; + /* can be modified without holding the LRU lock */ + atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; + atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; }; void lru_gen_init_lruvec(struct lruvec *lruvec); diff --git a/kernel/bounds.c b/kernel/bounds.c index e08fb89f87f476e8b287a00269d37062a8a95716..10dd9e6b03e551a1936587e02543b1c1883e201a 100644 --- a/kernel/bounds.c +++ b/kernel/bounds.c @@ -24,7 +24,7 @@ int main(void) DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t)); #ifdef CONFIG_LRU_GEN DEFINE(LRU_GEN_WIDTH, order_base_2(MAX_NR_GENS + 1)); - DEFINE(LRU_REFS_WIDTH, 0); + DEFINE(LRU_REFS_WIDTH, MAX_NR_TIERS - 2); #else DEFINE(LRU_GEN_WIDTH, 0); DEFINE(LRU_REFS_WIDTH, 0); diff --git a/mm/Kconfig b/mm/Kconfig index 5bde07cefa497cea9ee8e5554713d23d8b9a6d95..57aa760050f01aac7687eff9bd7703d7d260cc3d 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -985,6 +985,7 @@ config CLEAR_FREELIST_PAGE source "mm/damon/Kconfig" +# multi-gen LRU { config LRU_GEN bool "Multi-Gen LRU" depends on MMU @@ -993,4 +994,14 @@ config LRU_GEN help A high performance LRU implementation to overcommit memory. +config LRU_GEN_STATS + bool "Full stats for debugging" + depends on LRU_GEN + help + Do not enable this option unless you plan to look at historical stats + from evicted generations for debugging purpose. + + This option has a per-memcg and per-node memory overhead. +# } + endmenu diff --git a/mm/swap.c b/mm/swap.c index 0bdbb460a341899130370f4424b5fb43ddd07b12..acc56d3658b257bd1be293745c5ced00ed517658 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -401,6 +401,43 @@ static void __lru_cache_activate_page(struct page *page) local_unlock(&lru_pvecs.lock); } +#ifdef CONFIG_LRU_GEN +static void page_inc_refs(struct page *page) +{ + unsigned long refs; + unsigned long old_flags, new_flags; + + if (PageUnevictable(page)) + return; + + /* see the comment on MAX_NR_TIERS */ + do { + new_flags = old_flags = READ_ONCE(page->flags); + + if (!(new_flags & BIT(PG_referenced))) { + new_flags |= BIT(PG_referenced); + continue; + } + + if (!(new_flags & BIT(PG_workingset))) { + new_flags |= BIT(PG_workingset); + continue; + } + + refs = new_flags & LRU_REFS_MASK; + refs = min(refs + BIT(LRU_REFS_PGOFF), LRU_REFS_MASK); + + new_flags &= ~LRU_REFS_MASK; + new_flags |= refs; + } while (new_flags != old_flags && + cmpxchg(&page->flags, old_flags, new_flags) != old_flags); +} +#else +static void page_inc_refs(struct page *page) +{ +} +#endif /* CONFIG_LRU_GEN */ + /* * Mark a page as having seen activity. * @@ -415,6 +452,11 @@ void mark_page_accessed(struct page *page) { page = compound_head(page); + if (lru_gen_enabled()) { + page_inc_refs(page); + return; + } + if (!PageReferenced(page)) { SetPageReferenced(page); } else if (PageUnevictable(page)) { diff --git a/mm/vmscan.c b/mm/vmscan.c index 6e4df320a41ede66f4aeeb1c2550948392e6cf6c..b4f18890b3d3581a87f3d366df261b60f4d5d5a8 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1100,9 +1100,11 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, if (PageSwapCache(page)) { swp_entry_t swap = { .val = page_private(page) }; - mem_cgroup_swapout(page, swap); + + /* get a shadow entry before mem_cgroup_swapout() clears page_memcg() */ if (reclaimed && !mapping_exiting(mapping)) shadow = workingset_eviction(page, target_memcg); + mem_cgroup_swapout(page, swap); __delete_from_swap_cache(page, swap, shadow); xa_unlock_irqrestore(&mapping->i_pages, flags); put_swap_page(page, swap); @@ -2445,6 +2447,9 @@ static void prepare_scan_count(pg_data_t *pgdat, struct scan_control *sc) unsigned long file; struct lruvec *target_lruvec; + if (lru_gen_enabled()) + return; + target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); /* @@ -2748,11 +2753,38 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * shorthand helpers ******************************************************************************/ +#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 int page_lru_gen(struct page *page) +{ + unsigned long flags = READ_ONCE(page->flags); + + return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; +} + +static int page_lru_tier(struct page *page) +{ + int refs; + unsigned long flags = READ_ONCE(page->flags); + + refs = (flags & LRU_REFS_FLAGS) == LRU_REFS_FLAGS ? + ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + 1 : 0; + + return lru_tier_from_refs(refs); +} + static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid) { struct pglist_data *pgdat = NODE_DATA(nid); @@ -2773,6 +2805,753 @@ static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid) return pgdat ? &pgdat->__lruvec : NULL; } +static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc) +{ + struct mem_cgroup *memcg = lruvec_memcg(lruvec); + + if (mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH) + return 0; + + return mem_cgroup_swappiness(memcg); +} + +static int get_nr_gens(struct lruvec *lruvec, int type) +{ + return lruvec->lrugen.max_seq - lruvec->lrugen.min_seq[type] + 1; +} + +static bool __maybe_unused seq_is_valid(struct lruvec *lruvec) +{ + /* see the comment on lru_gen_struct */ + return get_nr_gens(lruvec, LRU_GEN_FILE) >= MIN_NR_GENS && + get_nr_gens(lruvec, LRU_GEN_FILE) <= get_nr_gens(lruvec, LRU_GEN_ANON) && + get_nr_gens(lruvec, LRU_GEN_ANON) <= MAX_NR_GENS; +} + +/****************************************************************************** + * refault feedback loop + ******************************************************************************/ + +/* + * A feedback loop based on Proportional-Integral-Derivative (PID) controller. + * + * The P term is refaulted/(evicted+protected) from a tier in the generation + * currently being evicted; the I term is the exponential moving average of the + * P term over the generations previously evicted, using the smoothing factor + * 1/2; the D term isn't supported. + * + * The setpoint (SP) is always the first tier of one type; the process variable + * (PV) is either any tier of the other type or any other tier of the same + * type. + * + * The error is the difference between the SP and the PV; the correction is + * turn off protection when SP>PV or turn on protection when SPlrugen; + 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 + ******************************************************************************/ + +static int page_inc_gen(struct lruvec *lruvec, struct page *page, bool reclaiming) +{ + unsigned long old_flags, new_flags; + int type = page_is_file_lru(page); + struct lru_gen_struct *lrugen = &lruvec->lrugen; + int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); + + do { + new_flags = old_flags = READ_ONCE(page->flags); + VM_BUG_ON_PAGE(!(new_flags & LRU_GEN_MASK), page); + + new_gen = (old_gen + 1) % MAX_NR_GENS; + + new_flags &= ~LRU_GEN_MASK; + new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF; + new_flags &= ~(LRU_REFS_MASK | LRU_REFS_FLAGS); + /* for end_page_writeback() */ + if (reclaiming) + new_flags |= BIT(PG_reclaim); + } while (cmpxchg(&page->flags, old_flags, new_flags) != old_flags); + + lru_gen_update_size(lruvec, page, old_gen, new_gen); + + return new_gen; +} + +static void inc_min_seq(struct lruvec *lruvec) +{ + int type; + struct lru_gen_struct *lrugen = &lruvec->lrugen; + + VM_BUG_ON(!seq_is_valid(lruvec)); + + for (type = 0; type < ANON_AND_FILE; type++) { + if (get_nr_gens(lruvec, type) != MAX_NR_GENS) + continue; + + reset_ctrl_pos(lruvec, type, true); + WRITE_ONCE(lrugen->min_seq[type], lrugen->min_seq[type] + 1); + } +} + +static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap) +{ + int gen, type, zone; + bool success = false; + struct lru_gen_struct *lrugen = &lruvec->lrugen; + DEFINE_MIN_SEQ(lruvec); + + VM_BUG_ON(!seq_is_valid(lruvec)); + + for (type = !can_swap; type < ANON_AND_FILE; type++) { + while (min_seq[type] + MIN_NR_GENS <= lrugen->max_seq) { + gen = lru_gen_from_seq(min_seq[type]); + + for (zone = 0; zone < MAX_NR_ZONES; zone++) { + if (!list_empty(&lrugen->lists[gen][type][zone])) + goto next; + } + + min_seq[type]++; + } +next: + ; + } + + /* see the comment on lru_gen_struct */ + if (can_swap) { + min_seq[LRU_GEN_ANON] = min(min_seq[LRU_GEN_ANON], min_seq[LRU_GEN_FILE]); + min_seq[LRU_GEN_FILE] = max(min_seq[LRU_GEN_ANON], lrugen->min_seq[LRU_GEN_FILE]); + } + + for (type = !can_swap; type < ANON_AND_FILE; type++) { + if (min_seq[type] == lrugen->min_seq[type]) + continue; + + reset_ctrl_pos(lruvec, type, true); + WRITE_ONCE(lrugen->min_seq[type], min_seq[type]); + success = true; + } + + return success; +} + +static void inc_max_seq(struct lruvec *lruvec, unsigned long max_seq) +{ + int prev, next; + int type, zone; + struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct pglist_data *pgdat = lruvec_pgdat(lruvec); + + spin_lock_irq(&lruvec->lru_lock); + + VM_BUG_ON(!seq_is_valid(lruvec)); + + if (max_seq != lrugen->max_seq) + goto unlock; + + inc_min_seq(lruvec); + + /* + * 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. This can be solved by moving + * pages from min_seq to min_seq+1 but is omitted for simplicity. + */ + 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; + + WARN_ON_ONCE(delta != (int)delta); + + __update_lru_size(lruvec, lru, zone, delta); + __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, -delta); + } + } + + for (type = 0; type < ANON_AND_FILE; type++) + reset_ctrl_pos(lruvec, type, false); + + /* make sure preceding modifications appear */ + smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1); +unlock: + spin_unlock_irq(&lruvec->lru_lock); +} + +static long get_nr_evictable(struct lruvec *lruvec, unsigned long max_seq, + unsigned long *min_seq, bool can_swap, bool *need_aging) +{ + int gen, type, zone; + long old = 0; + long young = 0; + long total = 0; + struct lru_gen_struct *lrugen = &lruvec->lrugen; + + for (type = !can_swap; type < ANON_AND_FILE; type++) { + unsigned long seq; + + for (seq = min_seq[type]; seq <= max_seq; seq++) { + long size = 0; + + gen = lru_gen_from_seq(seq); + + for (zone = 0; zone < MAX_NR_ZONES; zone++) + size += READ_ONCE(lrugen->nr_pages[gen][type][zone]); + + total += size; + if (seq == max_seq) + young += size; + if (seq + MIN_NR_GENS == max_seq) + old += size; + } + } + + /* + * The aging and the eviction is a typical producer-consumer model. The + * aging tries to be lazy to reduce the unnecessary overhead. On the + * other hand, the eviction stalls when the number of generations + * reaches MIN_NR_GENS. So ideally, there should be MIN_NR_GENS+1 + * generations, hence the first two if's. + * + * In addition, it's ideal to spread pages out evenly, meaning + * 1/(MIN_NR_GENS+1) of the total number of pages for each generation. A + * reasonable range for this average portion would [1/MIN_NR_GENS, + * 1/(MIN_NR_GENS+2)]. From the consumer's POV, the eviction only cares + * about the lower bound of cold pages, i.e., 1/(MIN_NR_GENS+2), whereas + * from the producer's POV, the aging only cares about the upper bound + * of hot pages, i.e., 1/MIN_NR_GENS. + */ + if (min_seq[LRU_GEN_FILE] + MIN_NR_GENS > max_seq) + *need_aging = true; + else if (min_seq[LRU_GEN_FILE] + MIN_NR_GENS < max_seq) + *need_aging = false; + else if (young * MIN_NR_GENS > total) + *need_aging = true; + else if (old * (MIN_NR_GENS + 2) < total) + *need_aging = true; + else + *need_aging = false; + + return total > 0 ? total : 0; +} + +static void age_lruvec(struct lruvec *lruvec, struct scan_control *sc) +{ + bool need_aging; + 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); + + mem_cgroup_calculate_protection(NULL, memcg); + + if (mem_cgroup_below_min(memcg)) + return; + + nr_to_scan = get_nr_evictable(lruvec, max_seq, min_seq, swappiness, &need_aging); + if (!nr_to_scan) + return; + + nr_to_scan >>= sc->priority; + + if (!mem_cgroup_online(memcg)) + nr_to_scan++; + + if (nr_to_scan && need_aging && (!mem_cgroup_below_low(memcg) || sc->memcg_low_reclaim)) + inc_max_seq(lruvec, max_seq); +} + +static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) +{ + struct mem_cgroup *memcg; + + VM_BUG_ON(!current_is_kswapd()); + + memcg = mem_cgroup_iter(NULL, NULL, NULL); + do { + struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); + + age_lruvec(lruvec, sc); + + cond_resched(); + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); +} + +/****************************************************************************** + * the eviction + ******************************************************************************/ + +static bool sort_page(struct lruvec *lruvec, struct page *page, int tier_idx) +{ + bool success; + int gen = page_lru_gen(page); + int type = page_is_file_lru(page); + int zone = page_zonenum(page); + int tier = page_lru_tier(page); + int delta = thp_nr_pages(page); + struct lru_gen_struct *lrugen = &lruvec->lrugen; + + VM_BUG_ON_PAGE(gen >= MAX_NR_GENS, page); + + if (!page_evictable(page)) { + success = lru_gen_del_page(lruvec, page, true); + VM_BUG_ON_PAGE(!success, page); + SetPageUnevictable(page); + add_page_to_lru_list(page, lruvec, page_lru(page)); + __count_vm_events(UNEVICTABLE_PGCULLED, delta); + return true; + } + + if (type == LRU_GEN_FILE && PageAnon(page) && PageDirty(page)) { + success = lru_gen_del_page(lruvec, page, true); + VM_BUG_ON_PAGE(!success, page); + SetPageSwapBacked(page); + add_page_to_lru_list_tail(page, lruvec, page_lru(page)); + return true; + } + + if (tier > tier_idx) { + int hist = lru_hist_from_seq(lrugen->min_seq[type]); + + gen = page_inc_gen(lruvec, page, false); + list_move_tail(&page->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; + } + + if (PageLocked(page) || PageWriteback(page) || + (type == LRU_GEN_FILE && PageDirty(page))) { + gen = page_inc_gen(lruvec, page, true); + list_move(&page->lru, &lrugen->lists[gen][type][zone]); + return true; + } + + return false; +} + +static bool isolate_page(struct lruvec *lruvec, struct page *page, struct scan_control *sc) +{ + bool success; + + if (!sc->may_unmap && page_mapped(page)) + return false; + + if (!(sc->may_writepage && (sc->gfp_mask & __GFP_IO)) && + (PageDirty(page) || (PageAnon(page) && !PageSwapCache(page)))) + return false; + + if (!get_page_unless_zero(page)) + return false; + + ClearPageLRU(page); + + success = lru_gen_del_page(lruvec, page, true); + VM_BUG_ON_PAGE(!success, page); + + return true; +} + +static int scan_pages(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_BUG_ON(!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 page *page = lru_to_page(head); + int delta = thp_nr_pages(page); + + VM_BUG_ON_PAGE(PageTail(page), page); + VM_BUG_ON_PAGE(PageUnevictable(page), page); + VM_BUG_ON_PAGE(PageActive(page), page); + VM_BUG_ON_PAGE(page_is_file_lru(page) != type, page); + VM_BUG_ON_PAGE(page_zonenum(page) != zone, page); + + prefetchw_prev_lru_page(page, head, flags); + + scanned += delta; + + if (sort_page(lruvec, page, tier)) + sorted += delta; + else if (isolate_page(lruvec, page, sc)) { + list_add(&page->lru, list); + isolated += delta; + } else { + list_move(&page->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 there is no + * 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_pages(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); + + VM_BUG_ON(!seq_is_valid(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_pages(lruvec, sc, type, tier, list); + if (scanned) + break; + + type = !type; + tier = -1; + } + + *type_scanned = type; + + return scanned; +} + +static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swappiness) +{ + int type; + int scanned; + int reclaimed; + LIST_HEAD(list); + struct page *page; + enum vm_event_item item; + struct reclaim_stat stat; + struct mem_cgroup *memcg = lruvec_memcg(lruvec); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); + + spin_lock_irq(&lruvec->lru_lock); + + scanned = isolate_pages(lruvec, sc, swappiness, &type, &list); + + if (try_to_inc_min_seq(lruvec, swappiness)) + scanned++; + + if (get_nr_gens(lruvec, LRU_GEN_FILE) == MIN_NR_GENS) + scanned = 0; + + spin_unlock_irq(&lruvec->lru_lock); + + if (list_empty(&list)) + return scanned; + + reclaimed = shrink_page_list(&list, pgdat, sc, &stat, false); + + /* + * To avoid livelock, don't add rejected pages back to the same lists + * they were isolated from. See lru_gen_add_page(). + */ + list_for_each_entry(page, &list, lru) { + ClearPageReferenced(page); + ClearPageWorkingset(page); + + if (PageReclaim(page) && (PageDirty(page) || PageWriteback(page))) + ClearPageActive(page); + else + SetPageActive(page); + } + + spin_lock_irq(&lruvec->lru_lock); + + move_pages_to_lru(lruvec, &list); + + item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT; + if (!cgroup_reclaim(sc)) + __count_vm_events(item, reclaimed); + __count_memcg_events(memcg, item, reclaimed); + __count_vm_events(PGSTEAL_ANON + type, reclaimed); + + spin_unlock_irq(&lruvec->lru_lock); + + mem_cgroup_uncharge_list(&list); + free_unref_page_list(&list); + + sc->nr_reclaimed += reclaimed; + + return scanned; +} + +static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool can_swap) +{ + bool need_aging; + 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; + + nr_to_scan = get_nr_evictable(lruvec, max_seq, min_seq, can_swap, &need_aging); + if (!nr_to_scan) + return 0; + + /* reset the priority if the target has been met */ + nr_to_scan >>= sc->nr_reclaimed < sc->nr_to_reclaim ? sc->priority : DEF_PRIORITY; + + if (!mem_cgroup_online(memcg)) + nr_to_scan++; + + if (!nr_to_scan) + return 0; + + if (!need_aging) + return nr_to_scan; + + /* leave the work to lru_gen_age_node() */ + if (current_is_kswapd()) + return 0; + + /* try other memcgs before going to the aging path */ + if (!cgroup_reclaim(sc) && !sc->force_deactivate) { + sc->skipped_deactivate = true; + return 0; + } + + inc_max_seq(lruvec, max_seq); + + return nr_to_scan; +} + +static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) +{ + struct blk_plug plug; + long scanned = 0; + + lru_add_drain(); + + blk_start_plug(&plug); + + while (true) { + int delta; + int swappiness; + long nr_to_scan; + + if (sc->may_swap) + swappiness = get_swappiness(lruvec, sc); + else if (!cgroup_reclaim(sc) && get_swappiness(lruvec, sc)) + swappiness = 1; + else + swappiness = 0; + + nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness); + if (!nr_to_scan) + break; + + delta = evict_pages(lruvec, sc, swappiness); + if (!delta) + break; + + scanned += delta; + if (scanned >= nr_to_scan) + break; + + cond_resched(); + } + + blk_finish_plug(&plug); +} + /****************************************************************************** * initialization ******************************************************************************/ @@ -2815,6 +3594,16 @@ static int __init init_lru_gen(void) }; late_initcall(init_lru_gen); +#else + +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) @@ -2828,6 +3617,11 @@ 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 */ @@ -3300,6 +4094,9 @@ static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat) struct lruvec *target_lruvec; unsigned long refaults; + if (lru_gen_enabled()) + return; + target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat); refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); target_lruvec->refaults[0] = refaults; @@ -3674,6 +4471,11 @@ static void age_active_anon(struct pglist_data *pgdat, struct mem_cgroup *memcg; struct lruvec *lruvec; + if (lru_gen_enabled()) { + lru_gen_age_node(pgdat, sc); + return; + } + if (!total_swap_pages) return; diff --git a/mm/workingset.c b/mm/workingset.c index 4a30e4a813a5d0d0925edd646fa0f9a8293cba72..18b242e364945dee4d2958319a7f224e7e01b19b 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -185,7 +185,6 @@ static unsigned int bucket_order __read_mostly; static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction, bool workingset) { - eviction >>= bucket_order; eviction &= EVICTION_MASK; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; eviction = (eviction << NODES_SHIFT) | pgdat->node_id; @@ -210,10 +209,116 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, *memcgidp = memcgid; *pgdat = NODE_DATA(nid); - *evictionp = entry << bucket_order; + *evictionp = entry; *workingsetp = workingset; } +#ifdef CONFIG_LRU_GEN + +static int page_lru_refs(struct page *page) +{ + unsigned long flags = READ_ONCE(page->flags); + + BUILD_BUG_ON(LRU_GEN_WIDTH + LRU_REFS_WIDTH > BITS_PER_LONG - EVICTION_SHIFT); + + /* see the comment on MAX_NR_TIERS */ + return flags & BIT(PG_workingset) ? (flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF : 0; +} + +static void *lru_gen_eviction(struct page *page) +{ + int hist, tier; + unsigned long token; + unsigned long min_seq; + struct lruvec *lruvec; + struct lru_gen_struct *lrugen; + int type = page_is_file_lru(page); + int refs = page_lru_refs(page); + int delta = thp_nr_pages(page); + bool workingset = PageWorkingset(page); + struct mem_cgroup *memcg = page_memcg(page); + struct pglist_data *pgdat = page_pgdat(page); + + lruvec = mem_cgroup_lruvec(memcg, pgdat); + lrugen = &lruvec->lrugen; + min_seq = READ_ONCE(lrugen->min_seq[type]); + token = (min_seq << LRU_REFS_WIDTH) | refs; + + hist = lru_hist_from_seq(min_seq); + tier = lru_tier_from_refs(refs + workingset); + atomic_long_add(delta, &lrugen->evicted[hist][type][tier]); + + return pack_shadow(mem_cgroup_id(memcg), pgdat, token, workingset); +} + +static void lru_gen_refault(struct page *page, void *shadow) +{ + int hist, tier, refs; + int memcg_id; + bool workingset; + unsigned long token; + unsigned long min_seq; + struct lruvec *lruvec; + struct lru_gen_struct *lrugen; + struct mem_cgroup *memcg; + struct pglist_data *pgdat; + int type = page_is_file_lru(page); + int delta = thp_nr_pages(page); + + unpack_shadow(shadow, &memcg_id, &pgdat, &token, &workingset); + + refs = token & (BIT(LRU_REFS_WIDTH) - 1); + if (refs && !workingset) + return; + + if (page_pgdat(page) != pgdat) + return; + + rcu_read_lock(); + memcg = page_memcg_rcu(page); + if (mem_cgroup_id(memcg) != memcg_id) + goto unlock; + + token >>= LRU_REFS_WIDTH; + lruvec = mem_cgroup_lruvec(memcg, pgdat); + lrugen = &lruvec->lrugen; + min_seq = READ_ONCE(lrugen->min_seq[type]); + if (token != (min_seq & (EVICTION_MASK >> LRU_REFS_WIDTH))) + goto unlock; + + hist = lru_hist_from_seq(min_seq); + tier = lru_tier_from_refs(refs + workingset); + atomic_long_add(delta, &lrugen->refaulted[hist][type][tier]); + mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + type, delta); + + /* + * Count the following two cases as stalls: + * 1. For pages accessed through page tables, hotter pages pushed out + * hot pages which refaulted immediately. + * 2. For pages accessed through file descriptors, numbers of accesses + * might have been beyond the limit. + */ + if (lru_gen_in_fault() || refs + workingset == BIT(LRU_REFS_WIDTH)) { + SetPageWorkingset(page); + mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta); + } +unlock: + rcu_read_unlock(); +} + +#else + +static void *lru_gen_eviction(struct page *page) +{ + return NULL; +} + +static void lru_gen_refault(struct page *page, void *shadow) +{ +} + +#endif /* CONFIG_LRU_GEN */ + /** * workingset_age_nonresident - age non-resident entries as LRU ages * @lruvec: the lruvec that was aged @@ -262,11 +367,15 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg) VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); + if (lru_gen_enabled()) + return lru_gen_eviction(page); + lruvec = mem_cgroup_lruvec(target_memcg, pgdat); workingset_age_nonresident(lruvec, thp_nr_pages(page)); /* XXX: target_memcg can be NULL, go through lruvec */ memcgid = mem_cgroup_id(lruvec_memcg(lruvec)); eviction = atomic_long_read(&lruvec->nonresident_age); + eviction >>= bucket_order; return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page)); } @@ -294,7 +403,13 @@ void workingset_refault(struct page *page, void *shadow) bool workingset; int memcgid; + if (lru_gen_enabled()) { + lru_gen_refault(page, shadow); + return; + } + unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset); + eviction <<= bucket_order; rcu_read_lock(); /*