From: Domenico Cerasuolo cerasuolodomenico@gmail.com
mainline inclusion from mainline-v6.8-rc1 commit a65b0e7607ccb5e5184591f73e48512f25c76061 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8ZUJQ CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
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.
[nphamcs@gmail.com: use correct function for the onlineness check, use mem_cgroup_iter_break()] Link: https://lkml.kernel.org/r/20231205195419.2563217-1-nphamcs@gmail.com [nphamcs@gmail.com: drop the pool's reference at the end of the writeback step] Link: https://lkml.kernel.org/r/20231206030627.4155634-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20231130194023.4102148-4-nphamcs@gmail.com Signed-off-by: Domenico Cerasuolo cerasuolodomenico@gmail.com Co-developed-by: Nhat Pham nphamcs@gmail.com Signed-off-by: Nhat Pham nphamcs@gmail.com Tested-by: Bagas Sanjaya bagasdotme@gmail.com Cc: Chris Li chrisl@kernel.org Cc: Dan Streetman ddstreet@ieee.org Cc: Johannes Weiner hannes@cmpxchg.org Cc: Michal Hocko mhocko@kernel.org Cc: Muchun Song muchun.song@linux.dev Cc: Roman Gushchin roman.gushchin@linux.dev Cc: Seth Jennings sjenning@redhat.com Cc: Shakeel Butt shakeelb@google.com Cc: Shuah Khan shuah@kernel.org Cc: Vitaly Wool vitaly.wool@konsulko.com Cc: Yosry Ahmed yosryahmed@google.com Signed-off-by: Andrew Morton akpm@linux-foundation.org
Conflicts: mm/swap_state.c mm/zswap.c Signed-off-by: Ma Wupeng mawupeng1@huawei.com --- include/linux/memcontrol.h | 5 + include/linux/zswap.h | 2 + mm/memcontrol.c | 3 + mm/swap.h | 3 +- mm/swap_state.c | 19 ++- mm/zswap.c | 268 ++++++++++++++++++++++++++++++------- 6 files changed, 243 insertions(+), 57 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b0ee904aa1b5..760302ac08f7 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1273,6 +1273,11 @@ 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 346be8292294..cb5f68870c07 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -67,6 +67,7 @@ #include <linux/sched/isolation.h> #include <linux/parser.h> #include <linux/dynamic_pool.h> +#include <linux/zswap.h>
#ifdef CONFIG_MEMCG_SWAP_QOS #include <linux/blkdev.h> @@ -6543,6 +6544,8 @@ 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 8a3c7a0ace4f..b54addaab860 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -50,7 +50,8 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr, - 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 vm_fault *vmf); struct page *swapin_readahead(swp_entry_t entry, gfp_t flag, diff --git a/mm/swap_state.c b/mm/swap_state.c index ddb3a65e5c6e..ceab83b90292 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -412,7 +412,7 @@ 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 vm_area_struct *vma, unsigned long addr, - bool *new_page_allocated) + bool *new_page_allocated, bool skip_if_exists) { struct swap_info_struct *si; struct folio *folio; @@ -469,6 +469,17 @@ 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 @@ -531,7 +542,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, { bool page_was_allocated; struct page *retpage = __read_swap_cache_async(entry, gfp_mask, - vma, addr, &page_was_allocated); + vma, addr, &page_was_allocated, false);
if (page_was_allocated) swap_readpage(retpage, false, plug); @@ -650,7 +661,7 @@ 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, vma, addr, &page_allocated); + gfp_mask, vma, addr, &page_allocated, false); if (!page) continue; if (page_allocated) { @@ -816,7 +827,7 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask, pte_unmap(pte); pte = NULL; page = __read_swap_cache_async(entry, gfp_mask, vma, - addr, &page_allocated); + addr, &page_allocated, false); if (!page) continue; if (page_allocated) { diff --git a/mm/zswap.c b/mm/zswap.c index 37d2b1cb2ecb..51a2a7ddda5e 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -34,6 +34,7 @@ #include <linux/writeback.h> #include <linux/pagemap.h> #include <linux/workqueue.h> +#include <linux/list_lru.h>
#include "swap.h" #include "internal.h" @@ -171,8 +172,8 @@ 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; };
/* @@ -288,15 +289,46 @@ static void zswap_update_total_size(void) zswap_pool_total_size = total; }
+/* should be called under RCU */ +#ifdef CONFIG_MEMCG +static inline struct mem_cgroup *mem_cgroup_from_entry(struct zswap_entry *entry) +{ + return entry->objcg ? obj_cgroup_memcg(entry->objcg) : NULL; +} +#else +static inline struct mem_cgroup *mem_cgroup_from_entry(struct zswap_entry *entry) +{ + return NULL; +} +#endif + +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(NULL, pool->next_shrink, NULL); + } + 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; @@ -309,6 +341,61 @@ 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 **********************************/ @@ -393,9 +480,7 @@ 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); } @@ -629,21 +714,15 @@ 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 @@ -651,28 +730,32 @@ 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 @@ -686,24 +769,91 @@ 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) + spin_lock(&zswap_pools_lock); + pool->next_shrink = mem_cgroup_iter(NULL, pool->next_shrink, NULL); + memcg = pool->next_shrink; + + /* + * We need to retry if we have gone through a full round trip, or if we + * got an offline memcg (or else we risk undoing the effect of the + * zswap memcg offlining cleanup callback). This is not catastrophic + * per se, but it will keep the now offlined memcg hostage for a while. + * + * Note that if we got an online memcg, we will keep the extra + * reference in case the original reference obtained by mem_cgroup_iter + * is dropped by the zswap memcg offlining callback, ensuring that the + * memcg is not killed when we are reclaiming. + */ + if (!memcg) { + spin_unlock(&zswap_pools_lock); + if (++failures == MAX_RECLAIM_RETRIES) break; + + goto resched; + } + + if (!mem_cgroup_tryget_online(memcg)) { + /* drop the reference from mem_cgroup_iter() */ + mem_cgroup_iter_break(NULL, memcg); + pool->next_shrink = NULL; + spin_unlock(&zswap_pools_lock); + if (++failures == MAX_RECLAIM_RETRIES) break; + + goto resched; } + spin_unlock(&zswap_pools_lock); + + ret = shrink_memcg(memcg); + /* drop the extra reference */ + 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); @@ -764,8 +914,7 @@ 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); @@ -831,6 +980,13 @@ 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_iter_break(NULL, 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); @@ -1076,7 +1232,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
/* try to allocate swap cache page */ page = __read_swap_cache_async(swpentry, GFP_KERNEL, NULL, 0, - &page_was_allocated); + &page_was_allocated, true); if (!page) { ret = -ENOMEM; goto fail; @@ -1142,7 +1298,6 @@ static int zswap_writeback_entry(struct zswap_entry *entry, /* start writeback */ __swap_writepage(page, &wbc); put_page(page); - zswap_written_back_pages++;
return ret;
@@ -1199,6 +1354,7 @@ 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; @@ -1230,15 +1386,15 @@ 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()) { @@ -1255,7 +1411,7 @@ 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; @@ -1282,6 +1438,15 @@ 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);
@@ -1358,9 +1523,8 @@ 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);
@@ -1373,6 +1537,7 @@ 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); @@ -1467,9 +1632,8 @@ 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);