From: Domenico Cerasuolo cerasuolodomenico@gmail.com

Currently, we only have a single global LRU for zswap. This makes it impossible to perform worload-specific shrinking - an memcg cannot determine which pages in the pool it owns, and often ends up writing pages from other memcgs. This issue has been previously observed in practice and mitigated by simply disabling memcg-initiated shrinking:

https://lore.kernel.org/all/20230530232435.3097106-1-nphamcs@gmail.com/T/#u

This patch fully resolves the issue by replacing the global zswap LRU with memcg- and NUMA-specific LRUs, and modify the reclaim logic:

a) When a store attempt hits an memcg limit, it now triggers a synchronous reclaim attempt that, if successful, allows the new hotter page to be accepted by zswap. b) If the store attempt instead hits the global zswap limit, it will trigger an asynchronous reclaim attempt, in which an memcg is selected for reclaim in a round-robin-like fashion.

Signed-off-by: Domenico Cerasuolo cerasuolodomenico@gmail.com Co-developed-by: Nhat Pham nphamcs@gmail.com Signed-off-by: Nhat Pham nphamcs@gmail.com --- include/linux/memcontrol.h | 5 + include/linux/zswap.h | 2 + mm/memcontrol.c | 2 + mm/swap.h | 3 +- mm/swap_state.c | 24 +++- mm/zswap.c | 248 +++++++++++++++++++++++++++++-------- 6 files changed, 223 insertions(+), 61 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5bfe41840e80..a568f70a2677 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1191,6 +1191,11 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) return NULL; }

+static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) +{ + return NULL; +} + static inline bool folio_memcg_kmem(struct folio *folio) { return false; diff --git a/include/linux/zswap.h b/include/linux/zswap.h index 2a60ce39cfde..e571e393669b 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -15,6 +15,7 @@ bool zswap_load(struct folio *folio); void zswap_invalidate(int type, pgoff_t offset); void zswap_swapon(int type); void zswap_swapoff(int type); +void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg);

#else

@@ -31,6 +32,7 @@ static inline bool zswap_load(struct folio *folio) static inline void zswap_invalidate(int type, pgoff_t offset) {} static inline void zswap_swapon(int type) {} static inline void zswap_swapoff(int type) {} +static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {}

#endif

diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b1fb96233fa1..8c0f3f971179 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5635,6 +5635,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) page_counter_set_min(&memcg->memory, 0); page_counter_set_low(&memcg->memory, 0);

+ zswap_memcg_offline_cleanup(memcg); + memcg_offline_kmem(memcg); reparent_shrinker_deferred(memcg); wb_memcg_offline(memcg); diff --git a/mm/swap.h b/mm/swap.h index 73c332ee4d91..c0dc73e10e91 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -51,7 +51,8 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct swap_iocb **plug); struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct mempolicy *mpol, pgoff_t ilx, - bool *new_page_allocated); + bool *new_page_allocated, + bool skip_if_exists); struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag, struct mempolicy *mpol, pgoff_t ilx); struct page *swapin_readahead(swp_entry_t entry, gfp_t flag, diff --git a/mm/swap_state.c b/mm/swap_state.c index 85d9e5806a6a..6c84236382f3 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -412,7 +412,8 @@ struct folio *filemap_get_incore_folio(struct address_space *mapping,

struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct mempolicy *mpol, pgoff_t ilx, - bool *new_page_allocated) + bool *new_page_allocated, + bool skip_if_exists) { struct swap_info_struct *si; struct folio *folio; @@ -470,6 +471,17 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, if (err != -EEXIST) goto fail_put_swap;

+ /* + * Protect against a recursive call to __read_swap_cache_async() + * on the same entry waiting forever here because SWAP_HAS_CACHE + * is set but the folio is not the swap cache yet. This can + * happen today if mem_cgroup_swapin_charge_folio() below + * triggers reclaim through zswap, which may call + * __read_swap_cache_async() in the writeback path. + */ + if (skip_if_exists) + goto fail_put_swap; + /* * We might race against __delete_from_swap_cache(), and * stumble across a swap_map entry whose SWAP_HAS_CACHE @@ -537,7 +549,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,

mpol = get_vma_policy(vma, addr, 0, &ilx); page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx, - &page_allocated); + &page_allocated, false); mpol_cond_put(mpol);

if (page_allocated) @@ -654,7 +666,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, /* Ok, do the async read-ahead now */ page = __read_swap_cache_async( swp_entry(swp_type(entry), offset), - gfp_mask, mpol, ilx, &page_allocated); + gfp_mask, mpol, ilx, &page_allocated, false); if (!page) continue; if (page_allocated) { @@ -672,7 +684,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, skip: /* The page was likely read above, so no need for plugging here */ page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx, - &page_allocated); + &page_allocated, false); if (unlikely(page_allocated)) swap_readpage(page, false, NULL); return page; @@ -827,7 +839,7 @@ static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask, pte_unmap(pte); pte = NULL; page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx, - &page_allocated); + &page_allocated, false); if (!page) continue; if (page_allocated) { @@ -847,7 +859,7 @@ static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask, skip: /* The page was likely read above, so no need for plugging here */ page = __read_swap_cache_async(targ_entry, gfp_mask, mpol, targ_ilx, - &page_allocated); + &page_allocated, false); if (unlikely(page_allocated)) swap_readpage(page, false, NULL); return page; diff --git a/mm/zswap.c b/mm/zswap.c index 4bdb2d83bb0d..5e397fc1f375 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -35,6 +35,7 @@ #include <linux/writeback.h> #include <linux/pagemap.h> #include <linux/workqueue.h> +#include <linux/list_lru.h>

#include "swap.h" #include "internal.h" @@ -174,8 +175,8 @@ struct zswap_pool { struct work_struct shrink_work; struct hlist_node node; char tfm_name[CRYPTO_MAX_ALG_NAME]; - struct list_head lru; - spinlock_t lru_lock; + struct list_lru list_lru; + struct mem_cgroup *next_shrink; };

/* @@ -291,15 +292,40 @@ static void zswap_update_total_size(void) zswap_pool_total_size = total; }

+/* should be called under RCU */ +static inline struct mem_cgroup *mem_cgroup_from_entry(struct zswap_entry *entry) +{ + return entry->objcg ? obj_cgroup_memcg(entry->objcg) : NULL; +} + +static inline int entry_to_nid(struct zswap_entry *entry) +{ + return page_to_nid(virt_to_page(entry)); +} + +void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) +{ + struct zswap_pool *pool; + + /* lock out zswap pools list modification */ + spin_lock(&zswap_pools_lock); + list_for_each_entry(pool, &zswap_pools, list) { + if (pool->next_shrink == memcg) + pool->next_shrink = + mem_cgroup_iter_online(NULL, pool->next_shrink, NULL, true); + } + spin_unlock(&zswap_pools_lock); +} + /********************************* * zswap entry functions **********************************/ static struct kmem_cache *zswap_entry_cache;

-static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp) +static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp, int nid) { struct zswap_entry *entry; - entry = kmem_cache_alloc(zswap_entry_cache, gfp); + entry = kmem_cache_alloc_node(zswap_entry_cache, gfp, nid); if (!entry) return NULL; entry->refcount = 1; @@ -312,6 +338,61 @@ static void zswap_entry_cache_free(struct zswap_entry *entry) kmem_cache_free(zswap_entry_cache, entry); }

+/********************************* +* lru functions +**********************************/ +static void zswap_lru_add(struct list_lru *list_lru, struct zswap_entry *entry) +{ + int nid = entry_to_nid(entry); + struct mem_cgroup *memcg; + + /* + * Note that it is safe to use rcu_read_lock() here, even in the face of + * concurrent memcg offlining. Thanks to the memcg->kmemcg_id indirection + * used in list_lru lookup, only two scenarios are possible: + * + * 1. list_lru_add() is called before memcg->kmemcg_id is updated. The + * new entry will be reparented to memcg's parent's list_lru. + * 2. list_lru_add() is called after memcg->kmemcg_id is updated. The + * new entry will be added directly to memcg's parent's list_lru. + * + * Similar reasoning holds for list_lru_del() and list_lru_putback(). + */ + rcu_read_lock(); + memcg = mem_cgroup_from_entry(entry); + /* will always succeed */ + list_lru_add(list_lru, &entry->lru, nid, memcg); + rcu_read_unlock(); +} + +static void zswap_lru_del(struct list_lru *list_lru, struct zswap_entry *entry) +{ + int nid = entry_to_nid(entry); + struct mem_cgroup *memcg; + + rcu_read_lock(); + memcg = mem_cgroup_from_entry(entry); + /* will always succeed */ + list_lru_del(list_lru, &entry->lru, nid, memcg); + rcu_read_unlock(); +} + +static void zswap_lru_putback(struct list_lru *list_lru, + struct zswap_entry *entry) +{ + int nid = entry_to_nid(entry); + spinlock_t *lock = &list_lru->node[nid].lock; + struct mem_cgroup *memcg; + + rcu_read_lock(); + memcg = mem_cgroup_from_entry(entry); + spin_lock(lock); + /* we cannot use list_lru_add here, because it increments node's lru count */ + list_lru_putback(list_lru, &entry->lru, nid, memcg); + spin_unlock(lock); + rcu_read_unlock(); +} + /********************************* * rbtree functions **********************************/ @@ -396,9 +477,7 @@ static void zswap_free_entry(struct zswap_entry *entry) if (!entry->length) atomic_dec(&zswap_same_filled_pages); else { - spin_lock(&entry->pool->lru_lock); - list_del(&entry->lru); - spin_unlock(&entry->pool->lru_lock); + zswap_lru_del(&entry->pool->list_lru, entry); zpool_free(zswap_find_zpool(entry), entry->handle); zswap_pool_put(entry->pool); } @@ -632,21 +711,15 @@ static void zswap_invalidate_entry(struct zswap_tree *tree, zswap_entry_put(tree, entry); }

-static int zswap_reclaim_entry(struct zswap_pool *pool) +static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l, + spinlock_t *lock, void *arg) { - struct zswap_entry *entry; + struct zswap_entry *entry = container_of(item, struct zswap_entry, lru); struct zswap_tree *tree; pgoff_t swpoffset; - int ret; + enum lru_status ret = LRU_REMOVED_RETRY; + int writeback_result;

- /* Get an entry off the LRU */ - spin_lock(&pool->lru_lock); - if (list_empty(&pool->lru)) { - spin_unlock(&pool->lru_lock); - return -EINVAL; - } - entry = list_last_entry(&pool->lru, struct zswap_entry, lru); - list_del_init(&entry->lru); /* * Once the lru lock is dropped, the entry might get freed. The * swpoffset is copied to the stack, and entry isn't deref'd again @@ -654,28 +727,32 @@ static int zswap_reclaim_entry(struct zswap_pool *pool) */ swpoffset = swp_offset(entry->swpentry); tree = zswap_trees[swp_type(entry->swpentry)]; - spin_unlock(&pool->lru_lock); + list_lru_isolate(l, item); + /* + * It's safe to drop the lock here because we return either + * LRU_REMOVED_RETRY or LRU_RETRY. + */ + spin_unlock(lock);

/* Check for invalidate() race */ spin_lock(&tree->lock); - if (entry != zswap_rb_search(&tree->rbroot, swpoffset)) { - ret = -EAGAIN; + if (entry != zswap_rb_search(&tree->rbroot, swpoffset)) goto unlock; - } + /* Hold a reference to prevent a free during writeback */ zswap_entry_get(entry); spin_unlock(&tree->lock);

- ret = zswap_writeback_entry(entry, tree); + writeback_result = zswap_writeback_entry(entry, tree);

spin_lock(&tree->lock); - if (ret) { - /* Writeback failed, put entry back on LRU */ - spin_lock(&pool->lru_lock); - list_move(&entry->lru, &pool->lru); - spin_unlock(&pool->lru_lock); + if (writeback_result) { + zswap_reject_reclaim_fail++; + zswap_lru_putback(&entry->pool->list_lru, entry); + ret = LRU_RETRY; goto put_unlock; } + zswap_written_back_pages++;

/* * Writeback started successfully, the page now belongs to the @@ -689,27 +766,76 @@ static int zswap_reclaim_entry(struct zswap_pool *pool) zswap_entry_put(tree, entry); unlock: spin_unlock(&tree->lock); - return ret ? -EAGAIN : 0; + spin_lock(lock); + return ret; +} + +static int shrink_memcg(struct mem_cgroup *memcg) +{ + struct zswap_pool *pool; + int nid, shrunk = 0; + + /* + * Skip zombies because their LRUs are reparented and we would be + * reclaiming from the parent instead of the dead memcg. + */ + if (memcg && !mem_cgroup_online(memcg)) + return -ENOENT; + + pool = zswap_pool_current_get(); + if (!pool) + return -EINVAL; + + for_each_node_state(nid, N_NORMAL_MEMORY) { + unsigned long nr_to_walk = 1; + + shrunk += list_lru_walk_one(&pool->list_lru, nid, memcg, + &shrink_memcg_cb, NULL, &nr_to_walk); + } + zswap_pool_put(pool); + return shrunk ? 0 : -EAGAIN; }

static void shrink_worker(struct work_struct *w) { struct zswap_pool *pool = container_of(w, typeof(*pool), shrink_work); + struct mem_cgroup *memcg; int ret, failures = 0;

+ /* global reclaim will select cgroup in a round-robin fashion. */ do { - ret = zswap_reclaim_entry(pool); - if (ret) { - zswap_reject_reclaim_fail++; - if (ret != -EAGAIN) - break; + spin_lock(&zswap_pools_lock); + memcg = pool->next_shrink = + mem_cgroup_iter_online(NULL, pool->next_shrink, NULL, true); + + /* full round trip */ + if (!memcg) { + spin_unlock(&zswap_pools_lock); if (++failures == MAX_RECLAIM_RETRIES) break; + + goto resched; } + + /* + * Acquire an extra reference to the iterated memcg in case the + * original reference is dropped by the zswap offlining callback. + */ + css_get(&memcg->css); + spin_unlock(&zswap_pools_lock); + + ret = shrink_memcg(memcg); + mem_cgroup_put(memcg); + + if (ret == -EINVAL) + break; + if (ret && ++failures == MAX_RECLAIM_RETRIES) + break; + +resched: cond_resched(); } while (!zswap_can_accept()); - zswap_pool_put(pool); }

static struct zswap_pool *zswap_pool_create(char *type, char *compressor) @@ -767,8 +893,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) */ kref_init(&pool->kref); INIT_LIST_HEAD(&pool->list); - INIT_LIST_HEAD(&pool->lru); - spin_lock_init(&pool->lru_lock); + list_lru_init_memcg(&pool->list_lru, NULL); INIT_WORK(&pool->shrink_work, shrink_worker);

zswap_pool_debug("created", pool); @@ -834,6 +959,13 @@ static void zswap_pool_destroy(struct zswap_pool *pool)

cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); free_percpu(pool->acomp_ctx); + list_lru_destroy(&pool->list_lru); + + spin_lock(&zswap_pools_lock); + mem_cgroup_put(pool->next_shrink); + pool->next_shrink = NULL; + spin_unlock(&zswap_pools_lock); + for (i = 0; i < ZSWAP_NR_ZPOOLS; i++) zpool_destroy_pool(pool->zpools[i]); kfree(pool); @@ -1081,7 +1213,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry, /* try to allocate swap cache page */ mpol = get_task_policy(current); page = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol, - NO_INTERLEAVE_INDEX, &page_was_allocated); + NO_INTERLEAVE_INDEX, &page_was_allocated, true); if (!page) { ret = -ENOMEM; goto fail; @@ -1152,7 +1284,6 @@ static int zswap_writeback_entry(struct zswap_entry *entry, /* start writeback */ __swap_writepage(page, &wbc); put_page(page); - zswap_written_back_pages++;

return ret;

@@ -1209,6 +1340,7 @@ bool zswap_store(struct folio *folio) struct scatterlist input, output; struct crypto_acomp_ctx *acomp_ctx; struct obj_cgroup *objcg = NULL; + struct mem_cgroup *memcg = NULL; struct zswap_pool *pool; struct zpool *zpool; unsigned int dlen = PAGE_SIZE; @@ -1240,15 +1372,15 @@ bool zswap_store(struct folio *folio) zswap_invalidate_entry(tree, dupentry); } spin_unlock(&tree->lock); - - /* - * XXX: zswap reclaim does not work with cgroups yet. Without a - * cgroup-aware entry LRU, we will push out entries system-wide based on - * local cgroup limits. - */ objcg = get_obj_cgroup_from_folio(folio); - if (objcg && !obj_cgroup_may_zswap(objcg)) - goto reject; + if (objcg && !obj_cgroup_may_zswap(objcg)) { + memcg = get_mem_cgroup_from_objcg(objcg); + if (shrink_memcg(memcg)) { + mem_cgroup_put(memcg); + goto reject; + } + mem_cgroup_put(memcg); + }

/* reclaim space if needed */ if (zswap_is_full()) { @@ -1265,7 +1397,7 @@ bool zswap_store(struct folio *folio) }

/* allocate entry */ - entry = zswap_entry_cache_alloc(GFP_KERNEL); + entry = zswap_entry_cache_alloc(GFP_KERNEL, page_to_nid(page)); if (!entry) { zswap_reject_kmemcache_fail++; goto reject; @@ -1292,6 +1424,15 @@ bool zswap_store(struct folio *folio) if (!entry->pool) goto freepage;

+ if (objcg) { + memcg = get_mem_cgroup_from_objcg(objcg); + if (memcg_list_lru_alloc(memcg, &entry->pool->list_lru, GFP_KERNEL)) { + mem_cgroup_put(memcg); + goto put_pool; + } + mem_cgroup_put(memcg); + } + /* compress */ acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);

@@ -1370,9 +1511,8 @@ bool zswap_store(struct folio *folio) zswap_invalidate_entry(tree, dupentry); } if (entry->length) { - spin_lock(&entry->pool->lru_lock); - list_add(&entry->lru, &entry->pool->lru); - spin_unlock(&entry->pool->lru_lock); + INIT_LIST_HEAD(&entry->lru); + zswap_lru_add(&entry->pool->list_lru, entry); } spin_unlock(&tree->lock);

@@ -1385,6 +1525,7 @@ bool zswap_store(struct folio *folio)

put_dstmem: mutex_unlock(acomp_ctx->mutex); +put_pool: zswap_pool_put(entry->pool); freepage: zswap_entry_cache_free(entry); @@ -1479,9 +1620,8 @@ bool zswap_load(struct folio *folio) zswap_invalidate_entry(tree, entry); folio_mark_dirty(folio); } else if (entry->length) { - spin_lock(&entry->pool->lru_lock); - list_move(&entry->lru, &entry->pool->lru); - spin_unlock(&entry->pool->lru_lock); + zswap_lru_del(&entry->pool->list_lru, entry); + zswap_lru_add(&entry->pool->list_lru, entry); } zswap_entry_put(tree, entry); spin_unlock(&tree->lock);

From: Domenico Cerasuolo cerasuolodomenico@gmail.com

Since zswap now writes back pages from memcg-specific LRUs, we now need a new stat to show writebacks count for each memcg.

Suggested-by: Nhat Pham nphamcs@gmail.com Signed-off-by: Domenico Cerasuolo cerasuolodomenico@gmail.com Signed-off-by: Nhat Pham nphamcs@gmail.com --- include/linux/vm_event_item.h | 1 + mm/memcontrol.c | 1 + mm/vmstat.c | 1 + mm/zswap.c | 3 +++ 4 files changed, 6 insertions(+)

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index d1b847502f09..f4569ad98edf 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -142,6 +142,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_ZSWAP ZSWPIN, ZSWPOUT, + ZSWP_WB, #endif #ifdef CONFIG_X86 DIRECT_MAP_LEVEL2_SPLIT, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8c0f3f971179..f88c8fd03689 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -703,6 +703,7 @@ static const unsigned int memcg_vm_event_stat[] = { #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) ZSWPIN, ZSWPOUT, + ZSWP_WB, #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE THP_FAULT_ALLOC, diff --git a/mm/vmstat.c b/mm/vmstat.c index afa5a38fcc9c..2249f85e4a87 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1401,6 +1401,7 @@ const char * const vmstat_text[] = { #ifdef CONFIG_ZSWAP "zswpin", "zswpout", + "zswp_wb", #endif #ifdef CONFIG_X86 "direct_map_level2_splits", diff --git a/mm/zswap.c b/mm/zswap.c index 5e397fc1f375..6a761753f979 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -754,6 +754,9 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o } zswap_written_back_pages++;

+ if (entry->objcg) + count_objcg_event(entry->objcg, ZSWP_WB); + /* * Writeback started successfully, the page now belongs to the * swapcache. Drop the entry from zswap - unless invalidate already

Currently, we only shrink the zswap pool when the user-defined limit is hit. This means that if we set the limit too high, cold data that are unlikely to be used again will reside in the pool, wasting precious memory. It is hard to predict how much zswap space will be needed ahead of time, as this depends on the workload (specifically, on factors such as memory access patterns and compressibility of the memory pages).

This patch implements a memcg- and NUMA-aware shrinker for zswap, that is initiated when there is memory pressure. The shrinker does not have any parameter that must be tuned by the user, and can be opted in or out on a per-memcg basis.

Furthermore, to make it more robust for many workloads and prevent overshrinking (i.e evicting warm pages that might be refaulted into memory), we build in the following heuristics:

* Estimate the number of warm pages residing in zswap, and attempt to protect this region of the zswap LRU. * Scale the number of freeable objects by an estimate of the memory saving factor. The better zswap compresses the data, the fewer pages we will evict to swap (as we will otherwise incur IO for relatively small memory saving). * During reclaim, if the shrinker encounters a page that is also being brought into memory, the shrinker will cautiously terminate its shrinking action, as this is a sign that it is touching the warmer region of the zswap LRU.

As a proof of concept, we ran the following synthetic benchmark: build the linux kernel in a memory-limited cgroup, and allocate some cold data in tmpfs to see if the shrinker could write them out and improved the overall performance. Depending on the amount of cold data generated, we observe from 14% to 35% reduction in kernel CPU time used in the kernel builds.

Signed-off-by: Nhat Pham nphamcs@gmail.com --- Documentation/admin-guide/mm/zswap.rst | 7 + include/linux/mmzone.h | 2 + include/linux/zswap.h | 25 +++- mm/mmzone.c | 1 + mm/swap_state.c | 2 + mm/zswap.c | 177 ++++++++++++++++++++++++- 6 files changed, 208 insertions(+), 6 deletions(-)

diff --git a/Documentation/admin-guide/mm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst index 45b98390e938..522ae22ccb84 100644 --- a/Documentation/admin-guide/mm/zswap.rst +++ b/Documentation/admin-guide/mm/zswap.rst @@ -153,6 +153,13 @@ attribute, e. g.::

Setting this parameter to 100 will disable the hysteresis.

+When there is a sizable amount of cold memory residing in the zswap pool, it +can be advantageous to proactively write these cold pages to swap and reclaim +the memory for other use cases. By default, the zswap shrinker is disabled. +User can enable it as follows: + + echo Y > /sys/module/zswap/parameters/shrinker_enabled + A debugfs interface is provided for various statistic about pool size, number of pages stored, same-value filled pages and various counters for the reasons pages are rejected. diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7b1816450bfc..b23bc5390240 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -22,6 +22,7 @@ #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/local_lock.h> +#include <linux/zswap.h> #include <asm/page.h>

/* Free memory management - zoned buddy allocator. */ @@ -641,6 +642,7 @@ struct lruvec { #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif + struct zswap_lruvec_state zswap_lruvec_state; };

/* Isolate for asynchronous migration */ diff --git a/include/linux/zswap.h b/include/linux/zswap.h index e571e393669b..03253a5965bb 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -5,20 +5,40 @@ #include <linux/types.h> #include <linux/mm_types.h>

+struct lruvec; + extern u64 zswap_pool_total_size; extern atomic_t zswap_stored_pages;

#ifdef CONFIG_ZSWAP

+struct zswap_lruvec_state { + /* + * Number of pages in zswap that should be protected from the shrinker. + * This number is an estimate of the following counts: + * + * a) Recent page faults. + * b) Recent insertion to the zswap LRU. This includes new zswap stores, + * as well as recent zswap LRU rotations. + * + * These pages are likely to be warm, and might incur IO if the are written + * to swap. + */ + atomic_long_t nr_zswap_protected; +}; + bool zswap_store(struct folio *folio); bool zswap_load(struct folio *folio); void zswap_invalidate(int type, pgoff_t offset); void zswap_swapon(int type); void zswap_swapoff(int type); void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg); - +void zswap_lruvec_state_init(struct lruvec *lruvec); +void zswap_lruvec_swapin(struct page *page); #else

+struct zswap_lruvec_state {}; + static inline bool zswap_store(struct folio *folio) { return false; @@ -33,7 +53,8 @@ static inline void zswap_invalidate(int type, pgoff_t offset) {} static inline void zswap_swapon(int type) {} static inline void zswap_swapoff(int type) {} static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {} - +static inline void zswap_lruvec_state_init(struct lruvec *lruvec) {} +static inline void zswap_lruvec_swapin(struct page *page) {} #endif

#endif /* _LINUX_ZSWAP_H */ diff --git a/mm/mmzone.c b/mm/mmzone.c index b594d3f268fe..c01896eca736 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -78,6 +78,7 @@ void lruvec_init(struct lruvec *lruvec)

memset(lruvec, 0, sizeof(struct lruvec)); spin_lock_init(&lruvec->lru_lock); + zswap_lruvec_state_init(lruvec);

for_each_lru(lru) INIT_LIST_HEAD(&lruvec->lists[lru]); diff --git a/mm/swap_state.c b/mm/swap_state.c index 6c84236382f3..94ed2d508db0 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -687,6 +687,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, &page_allocated, false); if (unlikely(page_allocated)) swap_readpage(page, false, NULL); + zswap_lruvec_swapin(page); return page; }

@@ -862,6 +863,7 @@ static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask, &page_allocated, false); if (unlikely(page_allocated)) swap_readpage(page, false, NULL); + zswap_lruvec_swapin(page); return page; }

diff --git a/mm/zswap.c b/mm/zswap.c index 6a761753f979..a3378b4c8e6e 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -148,6 +148,10 @@ module_param_named(exclusive_loads, zswap_exclusive_loads_enabled, bool, 0644); /* Number of zpools in zswap_pool (empirically determined for scalability) */ #define ZSWAP_NR_ZPOOLS 32

+/* Enable/disable memory pressure-based shrinker. */ +static bool zswap_shrinker_enabled; +module_param_named(shrinker_enabled, zswap_shrinker_enabled, bool, 0644); + /********************************* * data structures **********************************/ @@ -177,6 +181,8 @@ struct zswap_pool { char tfm_name[CRYPTO_MAX_ALG_NAME]; struct list_lru list_lru; struct mem_cgroup *next_shrink; + struct shrinker *shrinker; + atomic_t nr_stored; };

/* @@ -275,17 +281,26 @@ static bool zswap_can_accept(void) DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE); }

+static u64 get_zswap_pool_size(struct zswap_pool *pool) +{ + u64 pool_size = 0; + int i; + + for (i = 0; i < ZSWAP_NR_ZPOOLS; i++) + pool_size += zpool_get_total_size(pool->zpools[i]); + + return pool_size; +} + static void zswap_update_total_size(void) { struct zswap_pool *pool; u64 total = 0; - int i;

rcu_read_lock();

list_for_each_entry_rcu(pool, &zswap_pools, list) - for (i = 0; i < ZSWAP_NR_ZPOOLS; i++) - total += zpool_get_total_size(pool->zpools[i]); + total += get_zswap_pool_size(pool);

rcu_read_unlock();

@@ -338,13 +353,34 @@ static void zswap_entry_cache_free(struct zswap_entry *entry) kmem_cache_free(zswap_entry_cache, entry); }

+/********************************* +* zswap lruvec functions +**********************************/ +void zswap_lruvec_state_init(struct lruvec *lruvec) +{ + atomic_long_set(&lruvec->zswap_lruvec_state.nr_zswap_protected, 0); +} + +void zswap_lruvec_swapin(struct page *page) +{ + struct lruvec *lruvec; + + if (page) { + lruvec = folio_lruvec(page_folio(page)); + atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected); + } +} + /********************************* * lru functions **********************************/ static void zswap_lru_add(struct list_lru *list_lru, struct zswap_entry *entry) { + atomic_long_t *nr_zswap_protected; + unsigned long lru_size, old, new; int nid = entry_to_nid(entry); struct mem_cgroup *memcg; + struct lruvec *lruvec;

/* * Note that it is safe to use rcu_read_lock() here, even in the face of @@ -362,6 +398,19 @@ static void zswap_lru_add(struct list_lru *list_lru, struct zswap_entry *entry) memcg = mem_cgroup_from_entry(entry); /* will always succeed */ list_lru_add(list_lru, &entry->lru, nid, memcg); + + /* Update the protection area */ + lru_size = list_lru_count_one(list_lru, nid, memcg); + lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid)); + nr_zswap_protected = &lruvec->zswap_lruvec_state.nr_zswap_protected; + old = atomic_long_inc_return(nr_zswap_protected); + /* + * Decay to avoid overflow and adapt to changing workloads. + * This is based on LRU reclaim cost decaying heuristics. + */ + do { + new = old > lru_size / 4 ? old / 2 : old; + } while (!atomic_long_try_cmpxchg(nr_zswap_protected, &old, new)); rcu_read_unlock(); }

@@ -383,6 +432,7 @@ static void zswap_lru_putback(struct list_lru *list_lru, int nid = entry_to_nid(entry); spinlock_t *lock = &list_lru->node[nid].lock; struct mem_cgroup *memcg; + struct lruvec *lruvec;

rcu_read_lock(); memcg = mem_cgroup_from_entry(entry); @@ -390,6 +440,10 @@ static void zswap_lru_putback(struct list_lru *list_lru, /* we cannot use list_lru_add here, because it increments node's lru count */ list_lru_putback(list_lru, &entry->lru, nid, memcg); spin_unlock(lock); + + lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(entry_to_nid(entry))); + /* increment the protection area to account for the LRU rotation. */ + atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected); rcu_read_unlock(); }

@@ -479,6 +533,7 @@ static void zswap_free_entry(struct zswap_entry *entry) else { zswap_lru_del(&entry->pool->list_lru, entry); zpool_free(zswap_find_zpool(entry), entry->handle); + atomic_dec(&entry->pool->nr_stored); zswap_pool_put(entry->pool); } zswap_entry_cache_free(entry); @@ -520,6 +575,95 @@ static struct zswap_entry *zswap_entry_find_get(struct rb_root *root, return entry; }

+/********************************* +* shrinker functions +**********************************/ +static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l, + spinlock_t *lock, void *arg); + +static unsigned long zswap_shrinker_scan(struct shrinker *shrinker, + struct shrink_control *sc) +{ + struct lruvec *lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid)); + unsigned long shrink_ret, nr_protected, lru_size; + struct zswap_pool *pool = shrinker->private_data; + bool encountered_page_in_swapcache = false; + + nr_protected = + atomic_long_read(&lruvec->zswap_lruvec_state.nr_zswap_protected); + lru_size = list_lru_shrink_count(&pool->list_lru, sc); + + /* + * Abort if the shrinker is disabled or if we are shrinking into the + * protected region. + */ + if (!zswap_shrinker_enabled || nr_protected >= lru_size - sc->nr_to_scan) { + sc->nr_scanned = 0; + return SHRINK_STOP; + } + + shrink_ret = list_lru_shrink_walk(&pool->list_lru, sc, &shrink_memcg_cb, + &encountered_page_in_swapcache); + + if (encountered_page_in_swapcache) + return SHRINK_STOP; + + return shrink_ret ? shrink_ret : SHRINK_STOP; +} + +static unsigned long zswap_shrinker_count(struct shrinker *shrinker, + struct shrink_control *sc) +{ + struct zswap_pool *pool = shrinker->private_data; + struct mem_cgroup *memcg = sc->memcg; + struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(sc->nid)); + unsigned long nr_backing, nr_stored, nr_freeable, nr_protected; + +#ifdef CONFIG_MEMCG_KMEM + cgroup_rstat_flush(memcg->css.cgroup); + nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT; + nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED); +#else + /* use pool stats instead of memcg stats */ + nr_backing = get_zswap_pool_size(pool) >> PAGE_SHIFT; + nr_stored = atomic_read(&pool->nr_stored); +#endif + + if (!zswap_shrinker_enabled || !nr_stored) + return 0; + + nr_protected = + atomic_long_read(&lruvec->zswap_lruvec_state.nr_zswap_protected); + nr_freeable = list_lru_shrink_count(&pool->list_lru, sc); + /* + * Subtract the lru size by an estimate of the number of pages + * that should be protected. + */ + nr_freeable = nr_freeable > nr_protected ? nr_freeable - nr_protected : 0; + + /* + * Scale the number of freeable pages by the memory saving factor. + * This ensures that the better zswap compresses memory, the fewer + * pages we will evict to swap (as it will otherwise incur IO for + * relatively small memory saving). + */ + return mult_frac(nr_freeable, nr_backing, nr_stored); +} + +static void zswap_alloc_shrinker(struct zswap_pool *pool) +{ + pool->shrinker = + shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, "mm-zswap"); + if (!pool->shrinker) + return; + + pool->shrinker->private_data = pool; + pool->shrinker->scan_objects = zswap_shrinker_scan; + pool->shrinker->count_objects = zswap_shrinker_count; + pool->shrinker->batch = 0; + pool->shrinker->seeks = DEFAULT_SEEKS; +} + /********************************* * per-cpu code **********************************/ @@ -715,6 +859,7 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o spinlock_t *lock, void *arg) { struct zswap_entry *entry = container_of(item, struct zswap_entry, lru); + bool *encountered_page_in_swapcache = (bool *)arg; struct zswap_tree *tree; pgoff_t swpoffset; enum lru_status ret = LRU_REMOVED_RETRY; @@ -750,6 +895,17 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o zswap_reject_reclaim_fail++; zswap_lru_putback(&entry->pool->list_lru, entry); ret = LRU_RETRY; + + /* + * Encountering a page already in swap cache is a sign that we are shrinking + * into the warmer region. We should terminate shrinking (if we're in the dynamic + * shrinker context). + */ + if (writeback_result == -EEXIST && encountered_page_in_swapcache) { + ret = LRU_SKIP; + *encountered_page_in_swapcache = true; + } + goto put_unlock; } zswap_written_back_pages++; @@ -889,6 +1045,11 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) &pool->node); if (ret) goto error; + + zswap_alloc_shrinker(pool); + if (!pool->shrinker) + goto error; + pr_debug("using %s compressor\n", pool->tfm_name);

/* being the current pool takes 1 ref; this func expects the @@ -896,13 +1057,19 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) */ kref_init(&pool->kref); INIT_LIST_HEAD(&pool->list); - list_lru_init_memcg(&pool->list_lru, NULL); + if (list_lru_init_memcg(&pool->list_lru, pool->shrinker)) + goto lru_fail; + shrinker_register(pool->shrinker); INIT_WORK(&pool->shrink_work, shrink_worker); + atomic_set(&pool->nr_stored, 0);

zswap_pool_debug("created", pool);

return pool;

+lru_fail: + list_lru_destroy(&pool->list_lru); + shrinker_free(pool->shrinker); error: if (pool->acomp_ctx) free_percpu(pool->acomp_ctx); @@ -960,6 +1127,7 @@ static void zswap_pool_destroy(struct zswap_pool *pool)

zswap_pool_debug("destroying", pool);

+ shrinker_free(pool->shrinker); cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); free_percpu(pool->acomp_ctx); list_lru_destroy(&pool->list_lru); @@ -1516,6 +1684,7 @@ bool zswap_store(struct folio *folio) if (entry->length) { INIT_LIST_HEAD(&entry->lru); zswap_lru_add(&entry->pool->list_lru, entry); + atomic_inc(&entry->pool->nr_stored); } spin_unlock(&tree->lock);