diff options
Diffstat (limited to '')
| -rw-r--r-- | mm/workingset.c | 308 |
1 files changed, 224 insertions, 84 deletions
diff --git a/mm/workingset.c b/mm/workingset.c index 474186b76ced..ae7e984b23c6 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -6,6 +6,7 @@ */ #include <linux/memcontrol.h> +#include <linux/mm_inline.h> #include <linux/writeback.h> #include <linux/shmem_fs.h> #include <linux/pagemap.h> @@ -156,8 +157,8 @@ * * Implementation * - * For each node's file LRU lists, a counter for inactive evictions - * and activations is maintained (node->inactive_age). + * For each node's LRU lists, a counter for inactive evictions and + * activations is maintained (node->nonresident_age). * * On eviction, a snapshot of this counter (along with some bits to * identify the node) is stored in the now empty page cache @@ -167,8 +168,10 @@ * refault distance will immediately activate the refaulting page. */ +#define WORKINGSET_SHIFT 1 #define EVICTION_SHIFT ((BITS_PER_LONG - BITS_PER_XA_VALUE) + \ - 1 + NODES_SHIFT + MEM_CGROUP_ID_SHIFT) + WORKINGSET_SHIFT + NODES_SHIFT + \ + MEM_CGROUP_ID_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT) /* @@ -184,11 +187,10 @@ 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; - eviction = (eviction << 1) | workingset; + eviction = (eviction << WORKINGSET_SHIFT) | workingset; return xa_mk_value(eviction); } @@ -200,8 +202,8 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, int memcgid, nid; bool workingset; - workingset = entry & 1; - entry >>= 1; + workingset = entry & ((1UL << WORKINGSET_SHIFT) - 1); + entry >>= WORKINGSET_SHIFT; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); @@ -209,11 +211,118 @@ 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; } -static void advance_inactive_age(struct mem_cgroup *memcg, pg_data_t *pgdat) +#ifdef CONFIG_LRU_GEN + +static void *lru_gen_eviction(struct folio *folio) +{ + int hist; + unsigned long token; + unsigned long min_seq; + struct lruvec *lruvec; + struct lru_gen_struct *lrugen; + int type = folio_is_file_lru(folio); + int delta = folio_nr_pages(folio); + int refs = folio_lru_refs(folio); + int tier = lru_tier_from_refs(refs); + struct mem_cgroup *memcg = folio_memcg(folio); + struct pglist_data *pgdat = folio_pgdat(folio); + + BUILD_BUG_ON(LRU_GEN_WIDTH + LRU_REFS_WIDTH > BITS_PER_LONG - EVICTION_SHIFT); + + lruvec = mem_cgroup_lruvec(memcg, pgdat); + lrugen = &lruvec->lrugen; + min_seq = READ_ONCE(lrugen->min_seq[type]); + token = (min_seq << LRU_REFS_WIDTH) | max(refs - 1, 0); + + hist = lru_hist_from_seq(min_seq); + atomic_long_add(delta, &lrugen->evicted[hist][type][tier]); + + return pack_shadow(mem_cgroup_id(memcg), pgdat, token, refs); +} + +static void lru_gen_refault(struct folio *folio, 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 = folio_is_file_lru(folio); + int delta = folio_nr_pages(folio); + + unpack_shadow(shadow, &memcg_id, &pgdat, &token, &workingset); + + if (pgdat != folio_pgdat(folio)) + return; + + rcu_read_lock(); + + memcg = folio_memcg_rcu(folio); + if (memcg_id != mem_cgroup_id(memcg)) + goto unlock; + + lruvec = mem_cgroup_lruvec(memcg, pgdat); + lrugen = &lruvec->lrugen; + + min_seq = READ_ONCE(lrugen->min_seq[type]); + if ((token >> LRU_REFS_WIDTH) != (min_seq & (EVICTION_MASK >> LRU_REFS_WIDTH))) + goto unlock; + + hist = lru_hist_from_seq(min_seq); + /* see the comment in folio_lru_refs() */ + refs = (token & (BIT(LRU_REFS_WIDTH) - 1)) + workingset; + tier = lru_tier_from_refs(refs); + + atomic_long_add(delta, &lrugen->refaulted[hist][type][tier]); + mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + type, delta); + + /* + * Count the following two cases as stalls: + * 1. For pages accessed through page tables, hotter pages pushed out + * hot pages which refaulted immediately. + * 2. For pages accessed multiple times through file descriptors, + * numbers of accesses might have been out of the range. + */ + if (lru_gen_in_fault() || refs == BIT(LRU_REFS_WIDTH)) { + folio_set_workingset(folio); + mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta); + } +unlock: + rcu_read_unlock(); +} + +#else /* !CONFIG_LRU_GEN */ + +static void *lru_gen_eviction(struct folio *folio) +{ + return NULL; +} + +static void lru_gen_refault(struct folio *folio, void *shadow) +{ +} + +#endif /* CONFIG_LRU_GEN */ + +/** + * workingset_age_nonresident - age non-resident entries as LRU ages + * @lruvec: the lruvec that was aged + * @nr_pages: the number of pages to count + * + * As in-memory pages are aged, non-resident pages need to be aged as + * well, in order for the refault distances later on to be comparable + * to the in-memory dimensions. This function allows reclaim and LRU + * operations to drive the non-resident aging along in parallel. + */ +void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages) { /* * Reclaiming a cgroup means reclaiming all its children in a @@ -227,74 +336,83 @@ static void advance_inactive_age(struct mem_cgroup *memcg, pg_data_t *pgdat) * the root cgroup's, age as well. */ do { - struct lruvec *lruvec; - - lruvec = mem_cgroup_lruvec(memcg, pgdat); - atomic_long_inc(&lruvec->inactive_age); - } while (memcg && (memcg = parent_mem_cgroup(memcg))); + atomic_long_add(nr_pages, &lruvec->nonresident_age); + } while ((lruvec = parent_lruvec(lruvec))); } /** - * workingset_eviction - note the eviction of a page from memory + * workingset_eviction - note the eviction of a folio from memory * @target_memcg: the cgroup that is causing the reclaim - * @page: the page being evicted + * @folio: the folio being evicted * - * Returns a shadow entry to be stored in @page->mapping->i_pages in place - * of the evicted @page so that a later refault can be detected. + * Return: a shadow entry to be stored in @folio->mapping->i_pages in place + * of the evicted @folio so that a later refault can be detected. */ -void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg) +void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg) { - struct pglist_data *pgdat = page_pgdat(page); + struct pglist_data *pgdat = folio_pgdat(folio); unsigned long eviction; struct lruvec *lruvec; int memcgid; - /* Page is fully exclusive and pins page->mem_cgroup */ - VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON_PAGE(page_count(page), page); - VM_BUG_ON_PAGE(!PageLocked(page), page); + /* Folio is fully exclusive and pins folio's memory cgroup pointer */ + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); + VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); - advance_inactive_age(page_memcg(page), pgdat); + if (lru_gen_enabled()) + return lru_gen_eviction(folio); lruvec = mem_cgroup_lruvec(target_memcg, pgdat); /* XXX: target_memcg can be NULL, go through lruvec */ memcgid = mem_cgroup_id(lruvec_memcg(lruvec)); - eviction = atomic_long_read(&lruvec->inactive_age); - return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page)); + eviction = atomic_long_read(&lruvec->nonresident_age); + eviction >>= bucket_order; + workingset_age_nonresident(lruvec, folio_nr_pages(folio)); + return pack_shadow(memcgid, pgdat, eviction, + folio_test_workingset(folio)); } /** - * workingset_refault - evaluate the refault of a previously evicted page - * @page: the freshly allocated replacement page - * @shadow: shadow entry of the evicted page + * workingset_refault - Evaluate the refault of a previously evicted folio. + * @folio: The freshly allocated replacement folio. + * @shadow: Shadow entry of the evicted folio. * * Calculates and evaluates the refault distance of the previously - * evicted page in the context of the node and the memcg whose memory + * evicted folio in the context of the node and the memcg whose memory * pressure caused the eviction. */ -void workingset_refault(struct page *page, void *shadow) +void workingset_refault(struct folio *folio, void *shadow) { + bool file = folio_is_file_lru(folio); struct mem_cgroup *eviction_memcg; struct lruvec *eviction_lruvec; unsigned long refault_distance; + unsigned long workingset_size; struct pglist_data *pgdat; - unsigned long active_file; struct mem_cgroup *memcg; unsigned long eviction; struct lruvec *lruvec; unsigned long refault; bool workingset; int memcgid; + long nr; + + if (lru_gen_enabled()) { + lru_gen_refault(folio, shadow); + return; + } unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset); + eviction <<= bucket_order; rcu_read_lock(); /* * Look up the memcg associated with the stored ID. It might - * have been deleted since the page's eviction. + * have been deleted since the folio's eviction. * * Note that in rare events the ID could have been recycled - * for a new cgroup that refaults a shared page. This is + * for a new cgroup that refaults a shared folio. This is * impossible to tell from the available data. However, this * should be a rare and limited disturbance, and activations * are always speculative anyway. Ultimately, it's the aging @@ -309,21 +427,20 @@ void workingset_refault(struct page *page, void *shadow) if (!mem_cgroup_disabled() && !eviction_memcg) goto out; eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat); - refault = atomic_long_read(&eviction_lruvec->inactive_age); - active_file = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE); + refault = atomic_long_read(&eviction_lruvec->nonresident_age); /* * Calculate the refault distance * * The unsigned subtraction here gives an accurate distance - * across inactive_age overflows in most cases. There is a + * across nonresident_age overflows in most cases. There is a * special case: usually, shadow entries have a short lifetime * and are either refaulted or reclaimed along with the inode * before they get too old. But it is not impossible for the - * inactive_age to lap a shadow entry in the field, which can - * then result in a false small refault distance, leading to a - * false activation should this old entry actually refault - * again. However, earlier kernels used to deactivate + * nonresident_age to lap a shadow entry in the field, which + * can then result in a false small refault distance, leading + * to a false activation should this old entry actually + * refault again. However, earlier kernels used to deactivate * unconditionally with *every* reclaim invocation for the * longest time, so the occasional inappropriate activation * leading to pressure on the active list is not a problem. @@ -331,34 +448,53 @@ void workingset_refault(struct page *page, void *shadow) refault_distance = (refault - eviction) & EVICTION_MASK; /* - * The activation decision for this page is made at the level + * The activation decision for this folio is made at the level * where the eviction occurred, as that is where the LRU order - * during page reclaim is being determined. + * during folio reclaim is being determined. * - * However, the cgroup that will own the page is the one that + * However, the cgroup that will own the folio is the one that * is actually experiencing the refault event. */ - memcg = page_memcg(page); + nr = folio_nr_pages(folio); + memcg = folio_memcg(folio); lruvec = mem_cgroup_lruvec(memcg, pgdat); - inc_lruvec_state(lruvec, WORKINGSET_REFAULT); + mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr); + mem_cgroup_flush_stats_delayed(); /* * Compare the distance to the existing workingset size. We - * don't act on pages that couldn't stay resident even if all - * the memory was available to the page cache. + * don't activate pages that couldn't stay resident even if + * all the memory was available to the workingset. Whether + * workingset competition needs to consider anon or not depends + * on having swap. */ - if (refault_distance > active_file) + workingset_size = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE); + if (!file) { + workingset_size += lruvec_page_state(eviction_lruvec, + NR_INACTIVE_FILE); + } + if (mem_cgroup_get_nr_swap_pages(memcg) > 0) { + workingset_size += lruvec_page_state(eviction_lruvec, + NR_ACTIVE_ANON); + if (file) { + workingset_size += lruvec_page_state(eviction_lruvec, + NR_INACTIVE_ANON); + } + } + if (refault_distance > workingset_size) goto out; - SetPageActive(page); - advance_inactive_age(memcg, pgdat); - inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); + folio_set_active(folio); + workingset_age_nonresident(lruvec, nr); + mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file, nr); - /* Page was active prior to eviction */ + /* Folio was active prior to eviction */ if (workingset) { - SetPageWorkingset(page); - inc_lruvec_state(lruvec, WORKINGSET_RESTORE); + folio_set_workingset(folio); + /* XXX: Move to lru_cache_add() when it supports new vs putback */ + lru_note_cost_folio(folio); + mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file, nr); } out: rcu_read_unlock(); @@ -366,9 +502,9 @@ out: /** * workingset_activation - note a page activation - * @page: page that is being activated + * @folio: Folio that is being activated. */ -void workingset_activation(struct page *page) +void workingset_activation(struct folio *folio) { struct mem_cgroup *memcg; @@ -380,10 +516,10 @@ void workingset_activation(struct page *page) * XXX: See workingset_refault() - this should return * root_mem_cgroup even for !CONFIG_MEMCG. */ - memcg = page_memcg_rcu(page); + memcg = folio_memcg_rcu(folio); if (!mem_cgroup_disabled() && !memcg) goto out; - advance_inactive_age(memcg, page_pgdat(page)); + workingset_age_nonresident(folio_lruvec(folio), folio_nr_pages(folio)); out: rcu_read_unlock(); } @@ -400,10 +536,12 @@ out: * point where they would still be useful. */ -static struct list_lru shadow_nodes; +struct list_lru shadow_nodes; void workingset_update_node(struct xa_node *node) { + struct address_space *mapping; + /* * Track non-empty nodes that contain only shadow entries; * unlink those that contain pages or are being freed. @@ -412,17 +550,18 @@ void workingset_update_node(struct xa_node *node) * already where they should be. The list_empty() test is safe * as node->private_list is protected by the i_pages lock. */ - VM_WARN_ON_ONCE(!irqs_disabled()); /* For __inc_lruvec_page_state */ + mapping = container_of(node->array, struct address_space, i_pages); + lockdep_assert_held(&mapping->i_pages.xa_lock); if (node->count && node->count == node->nr_values) { if (list_empty(&node->private_list)) { list_lru_add(&shadow_nodes, &node->private_list); - __inc_lruvec_slab_state(node, WORKINGSET_NODES); + __inc_lruvec_kmem_state(node, WORKINGSET_NODES); } } else { if (!list_empty(&node->private_list)) { list_lru_del(&shadow_nodes, &node->private_list); - __dec_lruvec_slab_state(node, WORKINGSET_NODES); + __dec_lruvec_kmem_state(node, WORKINGSET_NODES); } } } @@ -435,6 +574,8 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, unsigned long pages; nodes = list_lru_shrink_count(&shadow_nodes, sc); + if (!nodes) + return SHRINK_EMPTY; /* * Approximate a reasonable limit for the nodes @@ -467,17 +608,16 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, for (pages = 0, i = 0; i < NR_LRU_LISTS; i++) pages += lruvec_page_state_local(lruvec, NR_LRU_BASE + i); - pages += lruvec_page_state_local(lruvec, NR_SLAB_RECLAIMABLE); - pages += lruvec_page_state_local(lruvec, NR_SLAB_UNRECLAIMABLE); + pages += lruvec_page_state_local( + lruvec, NR_SLAB_RECLAIMABLE_B) >> PAGE_SHIFT; + pages += lruvec_page_state_local( + lruvec, NR_SLAB_UNRECLAIMABLE_B) >> PAGE_SHIFT; } else #endif pages = node_present_pages(sc->nid); max_nodes = pages >> (XA_CHUNK_SHIFT - 3); - if (!nodes) - return SHRINK_EMPTY; - if (nodes <= max_nodes) return 0; return nodes - max_nodes; @@ -489,12 +629,11 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, void *arg) __must_hold(lru_lock) { struct xa_node *node = container_of(item, struct xa_node, private_list); - XA_STATE(xas, node->array, 0); struct address_space *mapping; int ret; /* - * Page cache insertions and deletions synchroneously maintain + * Page cache insertions and deletions synchronously maintain * the shadow node LRU under the i_pages lock and the * lru_lock. Because the page cache tree is emptied before * the inode can be destroyed, holding the lru_lock pins any @@ -514,8 +653,15 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, goto out; } + if (!spin_trylock(&mapping->host->i_lock)) { + xa_unlock(&mapping->i_pages); + spin_unlock_irq(lru_lock); + ret = LRU_RETRY; + goto out; + } + list_lru_isolate(lru, item); - __dec_lruvec_slab_state(node, WORKINGSET_NODES); + __dec_lruvec_kmem_state(node, WORKINGSET_NODES); spin_unlock(lru_lock); @@ -528,20 +674,14 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, goto out_invalid; if (WARN_ON_ONCE(node->count != node->nr_values)) goto out_invalid; - mapping->nrexceptional -= node->nr_values; - xas.xa_node = xa_parent_locked(&mapping->i_pages, node); - xas.xa_offset = node->offset; - xas.xa_shift = node->shift + XA_CHUNK_SHIFT; - xas_set_update(&xas, workingset_update_node); - /* - * We could store a shadow entry here which was the minimum of the - * shadow entries we were tracking ... - */ - xas_store(&xas, NULL); - __inc_lruvec_slab_state(node, WORKINGSET_NODERECLAIM); + xa_delete_node(node, workingset_update_node); + __inc_lruvec_kmem_state(node, WORKINGSET_NODERECLAIM); out_invalid: xa_unlock_irq(&mapping->i_pages); + if (mapping_shrinkable(mapping)) + inode_add_lru(mapping->host); + spin_unlock(&mapping->host->i_lock); ret = LRU_REMOVED_RETRY; out: cond_resched(); @@ -591,7 +731,7 @@ static int __init workingset_init(void) pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", timestamp_bits, max_order, bucket_order); - ret = prealloc_shrinker(&workingset_shadow_shrinker); + ret = prealloc_shrinker(&workingset_shadow_shrinker, "mm-shadow"); if (ret) goto err; ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key, |