diff options
Diffstat (limited to 'mm/memcontrol.c')
| -rw-r--r-- | mm/memcontrol.c | 8158 |
1 files changed, 3548 insertions, 4610 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c index af7f18b32389..be810c1fbfc3 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* memcontrol.c - Memory Controller * * Copyright IBM Corporation, 2007 @@ -20,25 +21,21 @@ * Unified hierarchy configuration model * Copyright (C) 2015 Red Hat, Inc., Johannes Weiner * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. + * Per memcg lru locking + * Copyright (C) 2020 Alibaba, Inc, Alex Shi */ +#include <linux/cgroup-defs.h> #include <linux/page_counter.h> #include <linux/memcontrol.h> #include <linux/cgroup.h> -#include <linux/mm.h> +#include <linux/cpuset.h> #include <linux/sched/mm.h> #include <linux/shmem_fs.h> #include <linux/hugetlb.h> #include <linux/pagemap.h> +#include <linux/pagevec.h> +#include <linux/vm_event_item.h> #include <linux/smp.h> #include <linux/page-flags.h> #include <linux/backing-dev.h> @@ -46,208 +43,72 @@ #include <linux/rcupdate.h> #include <linux/limits.h> #include <linux/export.h> +#include <linux/list.h> #include <linux/mutex.h> #include <linux/rbtree.h> #include <linux/slab.h> -#include <linux/swap.h> #include <linux/swapops.h> #include <linux/spinlock.h> -#include <linux/eventfd.h> -#include <linux/poll.h> -#include <linux/sort.h> #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/vmpressure.h> +#include <linux/memremap.h> #include <linux/mm_inline.h> #include <linux/swap_cgroup.h> #include <linux/cpu.h> #include <linux/oom.h> #include <linux/lockdep.h> -#include <linux/file.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> +#include <linux/psi.h> +#include <linux/seq_buf.h> +#include <linux/sched/isolation.h> +#include <linux/kmemleak.h> #include "internal.h" #include <net/sock.h> #include <net/ip.h> #include "slab.h" +#include "memcontrol-v1.h" #include <linux/uaccess.h> +#define CREATE_TRACE_POINTS +#include <trace/events/memcg.h> +#undef CREATE_TRACE_POINTS + #include <trace/events/vmscan.h> struct cgroup_subsys memory_cgrp_subsys __read_mostly; EXPORT_SYMBOL(memory_cgrp_subsys); struct mem_cgroup *root_mem_cgroup __read_mostly; +EXPORT_SYMBOL(root_mem_cgroup); -#define MEM_CGROUP_RECLAIM_RETRIES 5 +/* Active memory cgroup to use from an interrupt context */ +DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg); +EXPORT_PER_CPU_SYMBOL_GPL(int_active_memcg); /* Socket memory accounting disabled? */ -static bool cgroup_memory_nosocket; +static bool cgroup_memory_nosocket __ro_after_init; /* Kernel memory accounting disabled? */ -static bool cgroup_memory_nokmem; +static bool cgroup_memory_nokmem __ro_after_init; -/* Whether the swap controller is active */ -#ifdef CONFIG_MEMCG_SWAP -int do_swap_account __read_mostly; -#else -#define do_swap_account 0 +/* BPF memory accounting disabled? */ +static bool cgroup_memory_nobpf __ro_after_init; + +static struct kmem_cache *memcg_cachep; +static struct kmem_cache *memcg_pn_cachep; + +#ifdef CONFIG_CGROUP_WRITEBACK +static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq); #endif -/* Whether legacy memory+swap accounting is active */ -static bool do_memsw_account(void) +static inline bool task_is_dying(void) { - return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && do_swap_account; + return tsk_is_oom_victim(current) || fatal_signal_pending(current) || + (current->flags & PF_EXITING); } -static const char *const mem_cgroup_lru_names[] = { - "inactive_anon", - "active_anon", - "inactive_file", - "active_file", - "unevictable", -}; - -#define THRESHOLDS_EVENTS_TARGET 128 -#define SOFTLIMIT_EVENTS_TARGET 1024 -#define NUMAINFO_EVENTS_TARGET 1024 - -/* - * Cgroups above their limits are maintained in a RB-Tree, independent of - * their hierarchy representation - */ - -struct mem_cgroup_tree_per_node { - struct rb_root rb_root; - struct rb_node *rb_rightmost; - spinlock_t lock; -}; - -struct mem_cgroup_tree { - struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES]; -}; - -static struct mem_cgroup_tree soft_limit_tree __read_mostly; - -/* for OOM */ -struct mem_cgroup_eventfd_list { - struct list_head list; - struct eventfd_ctx *eventfd; -}; - -/* - * cgroup_event represents events which userspace want to receive. - */ -struct mem_cgroup_event { - /* - * memcg which the event belongs to. - */ - struct mem_cgroup *memcg; - /* - * eventfd to signal userspace about the event. - */ - struct eventfd_ctx *eventfd; - /* - * Each of these stored in a list by the cgroup. - */ - struct list_head list; - /* - * register_event() callback will be used to add new userspace - * waiter for changes related to this event. Use eventfd_signal() - * on eventfd to send notification to userspace. - */ - int (*register_event)(struct mem_cgroup *memcg, - struct eventfd_ctx *eventfd, const char *args); - /* - * unregister_event() callback will be called when userspace closes - * the eventfd or on cgroup removing. This callback must be set, - * if you want provide notification functionality. - */ - void (*unregister_event)(struct mem_cgroup *memcg, - struct eventfd_ctx *eventfd); - /* - * All fields below needed to unregister event when - * userspace closes eventfd. - */ - poll_table pt; - wait_queue_head_t *wqh; - wait_queue_entry_t wait; - struct work_struct remove; -}; - -static void mem_cgroup_threshold(struct mem_cgroup *memcg); -static void mem_cgroup_oom_notify(struct mem_cgroup *memcg); - -/* Stuffs for move charges at task migration. */ -/* - * Types of charges to be moved. - */ -#define MOVE_ANON 0x1U -#define MOVE_FILE 0x2U -#define MOVE_MASK (MOVE_ANON | MOVE_FILE) - -/* "mc" and its members are protected by cgroup_mutex */ -static struct move_charge_struct { - spinlock_t lock; /* for from, to */ - struct mm_struct *mm; - struct mem_cgroup *from; - struct mem_cgroup *to; - unsigned long flags; - unsigned long precharge; - unsigned long moved_charge; - unsigned long moved_swap; - struct task_struct *moving_task; /* a task moving charges */ - wait_queue_head_t waitq; /* a waitq for other context */ -} mc = { - .lock = __SPIN_LOCK_UNLOCKED(mc.lock), - .waitq = __WAIT_QUEUE_HEAD_INITIALIZER(mc.waitq), -}; - -/* - * Maximum loops in mem_cgroup_hierarchical_reclaim(), used for soft - * limit reclaim to prevent infinite loops, if they ever occur. - */ -#define MEM_CGROUP_MAX_RECLAIM_LOOPS 100 -#define MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS 2 - -enum charge_type { - MEM_CGROUP_CHARGE_TYPE_CACHE = 0, - MEM_CGROUP_CHARGE_TYPE_ANON, - MEM_CGROUP_CHARGE_TYPE_SWAPOUT, /* for accounting swapcache */ - MEM_CGROUP_CHARGE_TYPE_DROP, /* a page was unused swap cache */ - NR_CHARGE_TYPE, -}; - -/* for encoding cft->private value on file */ -enum res_type { - _MEM, - _MEMSWAP, - _OOM_TYPE, - _KMEM, - _TCP, -}; - -#define MEMFILE_PRIVATE(x, val) ((x) << 16 | (val)) -#define MEMFILE_TYPE(val) ((val) >> 16 & 0xffff) -#define MEMFILE_ATTR(val) ((val) & 0xffff) -/* Used for OOM nofiier */ -#define OOM_CONTROL (0) - -/* - * Iteration constructs for visiting all cgroups (under a tree). If - * loops are exited prematurely (break), mem_cgroup_iter_break() must - * be used for reference counting. - */ -#define for_each_mem_cgroup_tree(iter, root) \ - for (iter = mem_cgroup_iter(root, NULL, NULL); \ - iter != NULL; \ - iter = mem_cgroup_iter(root, iter, NULL)) - -#define for_each_mem_cgroup(iter) \ - for (iter = mem_cgroup_iter(NULL, NULL, NULL); \ - iter != NULL; \ - iter = mem_cgroup_iter(NULL, iter, NULL)) - /* Some nice accessors for the vmpressure. */ struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg) { @@ -256,211 +117,141 @@ struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg) return &memcg->vmpressure; } -struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr) +struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr) { - return &container_of(vmpr, struct mem_cgroup, vmpressure)->css; + return container_of(vmpr, struct mem_cgroup, vmpressure); } -#ifdef CONFIG_MEMCG_KMEM -/* - * This will be the memcg's index in each cache's ->memcg_params.memcg_caches. - * The main reason for not using cgroup id for this: - * this works better in sparse environments, where we have a lot of memcgs, - * but only a few kmem-limited. Or also, if we have, for instance, 200 - * memcgs, and none but the 200th is kmem-limited, we'd have to have a - * 200 entry array for that. - * - * The current size of the caches array is stored in memcg_nr_cache_ids. It - * will double each time we have to increase it. - */ -static DEFINE_IDA(memcg_cache_ida); -int memcg_nr_cache_ids; - -/* Protects memcg_nr_cache_ids */ -static DECLARE_RWSEM(memcg_cache_ids_sem); +#define SEQ_BUF_SIZE SZ_4K +#define CURRENT_OBJCG_UPDATE_BIT 0 +#define CURRENT_OBJCG_UPDATE_FLAG (1UL << CURRENT_OBJCG_UPDATE_BIT) -void memcg_get_cache_ids(void) -{ - down_read(&memcg_cache_ids_sem); -} +static DEFINE_SPINLOCK(objcg_lock); -void memcg_put_cache_ids(void) +bool mem_cgroup_kmem_disabled(void) { - up_read(&memcg_cache_ids_sem); + return cgroup_memory_nokmem; } -/* - * MIN_SIZE is different than 1, because we would like to avoid going through - * the alloc/free process all the time. In a small machine, 4 kmem-limited - * cgroups is a reasonable guess. In the future, it could be a parameter or - * tunable, but that is strictly not necessary. - * - * MAX_SIZE should be as large as the number of cgrp_ids. Ideally, we could get - * this constant directly from cgroup, but it is understandable that this is - * better kept as an internal representation in cgroup.c. In any case, the - * cgrp_id space is not getting any smaller, and we don't have to necessarily - * increase ours as well if it increases. - */ -#define MEMCG_CACHES_MIN_SIZE 4 -#define MEMCG_CACHES_MAX_SIZE MEM_CGROUP_ID_MAX - -/* - * A lot of the calls to the cache allocation functions are expected to be - * inlined by the compiler. Since the calls to memcg_kmem_get_cache are - * conditional to this static branch, we'll have to allow modules that does - * kmem_cache_alloc and the such to see this symbol as well - */ -DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key); -EXPORT_SYMBOL(memcg_kmem_enabled_key); - -struct workqueue_struct *memcg_kmem_cache_wq; - -static int memcg_shrinker_map_size; -static DEFINE_MUTEX(memcg_shrinker_map_mutex); +static void memcg_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages); -static void memcg_free_shrinker_map_rcu(struct rcu_head *head) +static void obj_cgroup_release(struct percpu_ref *ref) { - kvfree(container_of(head, struct memcg_shrinker_map, rcu)); -} - -static int memcg_expand_one_shrinker_map(struct mem_cgroup *memcg, - int size, int old_size) -{ - struct memcg_shrinker_map *new, *old; - int nid; - - lockdep_assert_held(&memcg_shrinker_map_mutex); - - for_each_node(nid) { - old = rcu_dereference_protected( - mem_cgroup_nodeinfo(memcg, nid)->shrinker_map, true); - /* Not yet online memcg */ - if (!old) - return 0; + struct obj_cgroup *objcg = container_of(ref, struct obj_cgroup, refcnt); + unsigned int nr_bytes; + unsigned int nr_pages; + unsigned long flags; - new = kvmalloc(sizeof(*new) + size, GFP_KERNEL); - if (!new) - return -ENOMEM; + /* + * At this point all allocated objects are freed, and + * objcg->nr_charged_bytes can't have an arbitrary byte value. + * However, it can be PAGE_SIZE or (x * PAGE_SIZE). + * + * The following sequence can lead to it: + * 1) CPU0: objcg == stock->cached_objcg + * 2) CPU1: we do a small allocation (e.g. 92 bytes), + * PAGE_SIZE bytes are charged + * 3) CPU1: a process from another memcg is allocating something, + * the stock if flushed, + * objcg->nr_charged_bytes = PAGE_SIZE - 92 + * 5) CPU0: we do release this object, + * 92 bytes are added to stock->nr_bytes + * 6) CPU0: stock is flushed, + * 92 bytes are added to objcg->nr_charged_bytes + * + * In the result, nr_charged_bytes == PAGE_SIZE. + * This page will be uncharged in obj_cgroup_release(). + */ + nr_bytes = atomic_read(&objcg->nr_charged_bytes); + WARN_ON_ONCE(nr_bytes & (PAGE_SIZE - 1)); + nr_pages = nr_bytes >> PAGE_SHIFT; - /* Set all old bits, clear all new bits */ - memset(new->map, (int)0xff, old_size); - memset((void *)new->map + old_size, 0, size - old_size); + if (nr_pages) { + struct mem_cgroup *memcg; - rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, new); - call_rcu(&old->rcu, memcg_free_shrinker_map_rcu); + memcg = get_mem_cgroup_from_objcg(objcg); + mod_memcg_state(memcg, MEMCG_KMEM, -nr_pages); + memcg1_account_kmem(memcg, -nr_pages); + if (!mem_cgroup_is_root(memcg)) + memcg_uncharge(memcg, nr_pages); + mem_cgroup_put(memcg); } - return 0; -} - -static void memcg_free_shrinker_maps(struct mem_cgroup *memcg) -{ - struct mem_cgroup_per_node *pn; - struct memcg_shrinker_map *map; - int nid; + spin_lock_irqsave(&objcg_lock, flags); + list_del(&objcg->list); + spin_unlock_irqrestore(&objcg_lock, flags); - if (mem_cgroup_is_root(memcg)) - return; - - for_each_node(nid) { - pn = mem_cgroup_nodeinfo(memcg, nid); - map = rcu_dereference_protected(pn->shrinker_map, true); - if (map) - kvfree(map); - rcu_assign_pointer(pn->shrinker_map, NULL); - } + percpu_ref_exit(ref); + kfree_rcu(objcg, rcu); } -static int memcg_alloc_shrinker_maps(struct mem_cgroup *memcg) +static struct obj_cgroup *obj_cgroup_alloc(void) { - struct memcg_shrinker_map *map; - int nid, size, ret = 0; + struct obj_cgroup *objcg; + int ret; - if (mem_cgroup_is_root(memcg)) - return 0; + objcg = kzalloc(sizeof(struct obj_cgroup), GFP_KERNEL); + if (!objcg) + return NULL; - mutex_lock(&memcg_shrinker_map_mutex); - size = memcg_shrinker_map_size; - for_each_node(nid) { - map = kvzalloc(sizeof(*map) + size, GFP_KERNEL); - if (!map) { - memcg_free_shrinker_maps(memcg); - ret = -ENOMEM; - break; - } - rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, map); + ret = percpu_ref_init(&objcg->refcnt, obj_cgroup_release, 0, + GFP_KERNEL); + if (ret) { + kfree(objcg); + return NULL; } - mutex_unlock(&memcg_shrinker_map_mutex); - - return ret; + INIT_LIST_HEAD(&objcg->list); + return objcg; } -int memcg_expand_shrinker_maps(int new_id) +static void memcg_reparent_objcgs(struct mem_cgroup *memcg, + struct mem_cgroup *parent) { - int size, old_size, ret = 0; - struct mem_cgroup *memcg; + struct obj_cgroup *objcg, *iter; - size = DIV_ROUND_UP(new_id + 1, BITS_PER_LONG) * sizeof(unsigned long); - old_size = memcg_shrinker_map_size; - if (size <= old_size) - return 0; + objcg = rcu_replace_pointer(memcg->objcg, NULL, true); - mutex_lock(&memcg_shrinker_map_mutex); - if (!root_mem_cgroup) - goto unlock; + spin_lock_irq(&objcg_lock); - for_each_mem_cgroup(memcg) { - if (mem_cgroup_is_root(memcg)) - continue; - ret = memcg_expand_one_shrinker_map(memcg, size, old_size); - if (ret) - goto unlock; - } -unlock: - if (!ret) - memcg_shrinker_map_size = size; - mutex_unlock(&memcg_shrinker_map_mutex); - return ret; -} + /* 1) Ready to reparent active objcg. */ + list_add(&objcg->list, &memcg->objcg_list); + /* 2) Reparent active objcg and already reparented objcgs to parent. */ + list_for_each_entry(iter, &memcg->objcg_list, list) + WRITE_ONCE(iter->memcg, parent); + /* 3) Move already reparented objcgs to the parent's list */ + list_splice(&memcg->objcg_list, &parent->objcg_list); -void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) -{ - if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { - struct memcg_shrinker_map *map; + spin_unlock_irq(&objcg_lock); - rcu_read_lock(); - map = rcu_dereference(memcg->nodeinfo[nid]->shrinker_map); - /* Pairs with smp mb in shrink_slab() */ - smp_mb__before_atomic(); - set_bit(shrinker_id, map->map); - rcu_read_unlock(); - } + percpu_ref_kill(&objcg->refcnt); } -#else /* CONFIG_MEMCG_KMEM */ -static int memcg_alloc_shrinker_maps(struct mem_cgroup *memcg) -{ - return 0; -} -static void memcg_free_shrinker_maps(struct mem_cgroup *memcg) { } -#endif /* CONFIG_MEMCG_KMEM */ +/* + * A lot of the calls to the cache allocation functions are expected to be + * inlined by the compiler. Since the calls to memcg_slab_post_alloc_hook() are + * conditional to this static branch, we'll have to allow modules that does + * kmem_cache_alloc and the such to see this symbol as well + */ +DEFINE_STATIC_KEY_FALSE(memcg_kmem_online_key); +EXPORT_SYMBOL(memcg_kmem_online_key); + +DEFINE_STATIC_KEY_FALSE(memcg_bpf_enabled_key); +EXPORT_SYMBOL(memcg_bpf_enabled_key); /** - * mem_cgroup_css_from_page - css of the memcg associated with a page - * @page: page of interest + * mem_cgroup_css_from_folio - css of the memcg associated with a folio + * @folio: folio of interest * * If memcg is bound to the default hierarchy, css of the memcg associated - * with @page is returned. The returned css remains associated with @page + * with @folio is returned. The returned css remains associated with @folio * until it is released. * * If memcg is bound to a traditional hierarchy, the css of root_mem_cgroup * is returned. */ -struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page) +struct cgroup_subsys_state *mem_cgroup_css_from_folio(struct folio *folio) { - struct mem_cgroup *memcg; - - memcg = page->mem_cgroup; + struct mem_cgroup *memcg = folio_memcg(folio); if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) memcg = root_mem_cgroup; @@ -487,7 +278,9 @@ ino_t page_cgroup_ino(struct page *page) unsigned long ino = 0; rcu_read_lock(); - memcg = READ_ONCE(page->mem_cgroup); + /* page_folio() is racy here, but the entire function is racy anyway */ + memcg = folio_memcg_check(page_folio(page)); + while (memcg && !(memcg->css.flags & CSS_ONLINE)) memcg = parent_mem_cgroup(memcg); if (memcg) @@ -495,312 +288,589 @@ ino_t page_cgroup_ino(struct page *page) rcu_read_unlock(); return ino; } +EXPORT_SYMBOL_GPL(page_cgroup_ino); + +/* Subset of node_stat_item for memcg stats */ +static const unsigned int memcg_node_stat_items[] = { + NR_INACTIVE_ANON, + NR_ACTIVE_ANON, + NR_INACTIVE_FILE, + NR_ACTIVE_FILE, + NR_UNEVICTABLE, + NR_SLAB_RECLAIMABLE_B, + NR_SLAB_UNRECLAIMABLE_B, + WORKINGSET_REFAULT_ANON, + WORKINGSET_REFAULT_FILE, + WORKINGSET_ACTIVATE_ANON, + WORKINGSET_ACTIVATE_FILE, + WORKINGSET_RESTORE_ANON, + WORKINGSET_RESTORE_FILE, + WORKINGSET_NODERECLAIM, + NR_ANON_MAPPED, + NR_FILE_MAPPED, + NR_FILE_PAGES, + NR_FILE_DIRTY, + NR_WRITEBACK, + NR_SHMEM, + NR_SHMEM_THPS, + NR_FILE_THPS, + NR_ANON_THPS, + NR_KERNEL_STACK_KB, + NR_PAGETABLE, + NR_SECONDARY_PAGETABLE, +#ifdef CONFIG_SWAP + NR_SWAPCACHE, +#endif +#ifdef CONFIG_NUMA_BALANCING + PGPROMOTE_SUCCESS, +#endif + PGDEMOTE_KSWAPD, + PGDEMOTE_DIRECT, + PGDEMOTE_KHUGEPAGED, + PGDEMOTE_PROACTIVE, +#ifdef CONFIG_HUGETLB_PAGE + NR_HUGETLB, +#endif +}; + +static const unsigned int memcg_stat_items[] = { + MEMCG_SWAP, + MEMCG_SOCK, + MEMCG_PERCPU_B, + MEMCG_VMALLOC, + MEMCG_KMEM, + MEMCG_ZSWAP_B, + MEMCG_ZSWAPPED, +}; -static struct mem_cgroup_per_node * -mem_cgroup_page_nodeinfo(struct mem_cgroup *memcg, struct page *page) +#define NR_MEMCG_NODE_STAT_ITEMS ARRAY_SIZE(memcg_node_stat_items) +#define MEMCG_VMSTAT_SIZE (NR_MEMCG_NODE_STAT_ITEMS + \ + ARRAY_SIZE(memcg_stat_items)) +#define BAD_STAT_IDX(index) ((u32)(index) >= U8_MAX) +static u8 mem_cgroup_stats_index[MEMCG_NR_STAT] __read_mostly; + +static void init_memcg_stats(void) { - int nid = page_to_nid(page); + u8 i, j = 0; + + BUILD_BUG_ON(MEMCG_NR_STAT >= U8_MAX); + + memset(mem_cgroup_stats_index, U8_MAX, sizeof(mem_cgroup_stats_index)); - return memcg->nodeinfo[nid]; + for (i = 0; i < NR_MEMCG_NODE_STAT_ITEMS; ++i, ++j) + mem_cgroup_stats_index[memcg_node_stat_items[i]] = j; + + for (i = 0; i < ARRAY_SIZE(memcg_stat_items); ++i, ++j) + mem_cgroup_stats_index[memcg_stat_items[i]] = j; } -static struct mem_cgroup_tree_per_node * -soft_limit_tree_node(int nid) +static inline int memcg_stats_index(int idx) { - return soft_limit_tree.rb_tree_per_node[nid]; + return mem_cgroup_stats_index[idx]; } -static struct mem_cgroup_tree_per_node * -soft_limit_tree_from_page(struct page *page) +struct lruvec_stats_percpu { + /* Local (CPU and cgroup) state */ + long state[NR_MEMCG_NODE_STAT_ITEMS]; + + /* Delta calculation for lockless upward propagation */ + long state_prev[NR_MEMCG_NODE_STAT_ITEMS]; +}; + +struct lruvec_stats { + /* Aggregated (CPU and subtree) state */ + long state[NR_MEMCG_NODE_STAT_ITEMS]; + + /* Non-hierarchical (CPU aggregated) state */ + long state_local[NR_MEMCG_NODE_STAT_ITEMS]; + + /* Pending child counts during tree propagation */ + long state_pending[NR_MEMCG_NODE_STAT_ITEMS]; +}; + +unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { - int nid = page_to_nid(page); + struct mem_cgroup_per_node *pn; + long x; + int i; - return soft_limit_tree.rb_tree_per_node[nid]; + if (mem_cgroup_disabled()) + return node_page_state(lruvec_pgdat(lruvec), idx); + + i = memcg_stats_index(idx); + if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx)) + return 0; + + pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + x = READ_ONCE(pn->lruvec_stats->state[i]); +#ifdef CONFIG_SMP + if (x < 0) + x = 0; +#endif + return x; } -static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz, - struct mem_cgroup_tree_per_node *mctz, - unsigned long new_usage_in_excess) +unsigned long lruvec_page_state_local(struct lruvec *lruvec, + enum node_stat_item idx) { - struct rb_node **p = &mctz->rb_root.rb_node; - struct rb_node *parent = NULL; - struct mem_cgroup_per_node *mz_node; - bool rightmost = true; + struct mem_cgroup_per_node *pn; + long x; + int i; - if (mz->on_tree) - return; + if (mem_cgroup_disabled()) + return node_page_state(lruvec_pgdat(lruvec), idx); + + i = memcg_stats_index(idx); + if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx)) + return 0; + + pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + x = READ_ONCE(pn->lruvec_stats->state_local[i]); +#ifdef CONFIG_SMP + if (x < 0) + x = 0; +#endif + return x; +} + +/* Subset of vm_event_item to report for memcg event stats */ +static const unsigned int memcg_vm_event_stat[] = { +#ifdef CONFIG_MEMCG_V1 + PGPGIN, + PGPGOUT, +#endif + PSWPIN, + PSWPOUT, + PGSCAN_KSWAPD, + PGSCAN_DIRECT, + PGSCAN_KHUGEPAGED, + PGSCAN_PROACTIVE, + PGSTEAL_KSWAPD, + PGSTEAL_DIRECT, + PGSTEAL_KHUGEPAGED, + PGSTEAL_PROACTIVE, + PGFAULT, + PGMAJFAULT, + PGREFILL, + PGACTIVATE, + PGDEACTIVATE, + PGLAZYFREE, + PGLAZYFREED, +#ifdef CONFIG_SWAP + SWPIN_ZERO, + SWPOUT_ZERO, +#endif +#ifdef CONFIG_ZSWAP + ZSWPIN, + ZSWPOUT, + ZSWPWB, +#endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + THP_FAULT_ALLOC, + THP_COLLAPSE_ALLOC, + THP_SWPOUT, + THP_SWPOUT_FALLBACK, +#endif +#ifdef CONFIG_NUMA_BALANCING + NUMA_PAGE_MIGRATE, + NUMA_PTE_UPDATES, + NUMA_HINT_FAULTS, +#endif +}; + +#define NR_MEMCG_EVENTS ARRAY_SIZE(memcg_vm_event_stat) +static u8 mem_cgroup_events_index[NR_VM_EVENT_ITEMS] __read_mostly; + +static void init_memcg_events(void) +{ + u8 i; - mz->usage_in_excess = new_usage_in_excess; - if (!mz->usage_in_excess) + BUILD_BUG_ON(NR_VM_EVENT_ITEMS >= U8_MAX); + + memset(mem_cgroup_events_index, U8_MAX, + sizeof(mem_cgroup_events_index)); + + for (i = 0; i < NR_MEMCG_EVENTS; ++i) + mem_cgroup_events_index[memcg_vm_event_stat[i]] = i; +} + +static inline int memcg_events_index(enum vm_event_item idx) +{ + return mem_cgroup_events_index[idx]; +} + +struct memcg_vmstats_percpu { + /* Stats updates since the last flush */ + unsigned int stats_updates; + + /* Cached pointers for fast iteration in memcg_rstat_updated() */ + struct memcg_vmstats_percpu __percpu *parent_pcpu; + struct memcg_vmstats *vmstats; + + /* The above should fit a single cacheline for memcg_rstat_updated() */ + + /* Local (CPU and cgroup) page state & events */ + long state[MEMCG_VMSTAT_SIZE]; + unsigned long events[NR_MEMCG_EVENTS]; + + /* Delta calculation for lockless upward propagation */ + long state_prev[MEMCG_VMSTAT_SIZE]; + unsigned long events_prev[NR_MEMCG_EVENTS]; +} ____cacheline_aligned; + +struct memcg_vmstats { + /* Aggregated (CPU and subtree) page state & events */ + long state[MEMCG_VMSTAT_SIZE]; + unsigned long events[NR_MEMCG_EVENTS]; + + /* Non-hierarchical (CPU aggregated) page state & events */ + long state_local[MEMCG_VMSTAT_SIZE]; + unsigned long events_local[NR_MEMCG_EVENTS]; + + /* Pending child counts during tree propagation */ + long state_pending[MEMCG_VMSTAT_SIZE]; + unsigned long events_pending[NR_MEMCG_EVENTS]; + + /* Stats updates since the last flush */ + atomic_t stats_updates; +}; + +/* + * memcg and lruvec stats flushing + * + * Many codepaths leading to stats update or read are performance sensitive and + * adding stats flushing in such codepaths is not desirable. So, to optimize the + * flushing the kernel does: + * + * 1) Periodically and asynchronously flush the stats every 2 seconds to not let + * rstat update tree grow unbounded. + * + * 2) Flush the stats synchronously on reader side only when there are more than + * (MEMCG_CHARGE_BATCH * nr_cpus) update events. Though this optimization + * will let stats be out of sync by atmost (MEMCG_CHARGE_BATCH * nr_cpus) but + * only for 2 seconds due to (1). + */ +static void flush_memcg_stats_dwork(struct work_struct *w); +static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork); +static u64 flush_last_time; + +#define FLUSH_TIME (2UL*HZ) + +static bool memcg_vmstats_needs_flush(struct memcg_vmstats *vmstats) +{ + return atomic_read(&vmstats->stats_updates) > + MEMCG_CHARGE_BATCH * num_online_cpus(); +} + +static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val, + int cpu) +{ + struct memcg_vmstats_percpu __percpu *statc_pcpu; + struct memcg_vmstats_percpu *statc; + unsigned int stats_updates; + + if (!val) return; - while (*p) { - parent = *p; - mz_node = rb_entry(parent, struct mem_cgroup_per_node, - tree_node); - if (mz->usage_in_excess < mz_node->usage_in_excess) { - p = &(*p)->rb_left; - rightmost = false; - } + css_rstat_updated(&memcg->css, cpu); + statc_pcpu = memcg->vmstats_percpu; + for (; statc_pcpu; statc_pcpu = statc->parent_pcpu) { + statc = this_cpu_ptr(statc_pcpu); /* - * We can't avoid mem cgroups that are over their soft - * limit by the same amount + * If @memcg is already flushable then all its ancestors are + * flushable as well and also there is no need to increase + * stats_updates. */ - else if (mz->usage_in_excess >= mz_node->usage_in_excess) - p = &(*p)->rb_right; + if (memcg_vmstats_needs_flush(statc->vmstats)) + break; + + stats_updates = this_cpu_add_return(statc_pcpu->stats_updates, + abs(val)); + if (stats_updates < MEMCG_CHARGE_BATCH) + continue; + + stats_updates = this_cpu_xchg(statc_pcpu->stats_updates, 0); + atomic_add(stats_updates, &statc->vmstats->stats_updates); } +} - if (rightmost) - mctz->rb_rightmost = &mz->tree_node; +static void __mem_cgroup_flush_stats(struct mem_cgroup *memcg, bool force) +{ + bool needs_flush = memcg_vmstats_needs_flush(memcg->vmstats); - rb_link_node(&mz->tree_node, parent, p); - rb_insert_color(&mz->tree_node, &mctz->rb_root); - mz->on_tree = true; + trace_memcg_flush_stats(memcg, atomic_read(&memcg->vmstats->stats_updates), + force, needs_flush); + + if (!force && !needs_flush) + return; + + if (mem_cgroup_is_root(memcg)) + WRITE_ONCE(flush_last_time, jiffies_64); + + css_rstat_flush(&memcg->css); } -static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz, - struct mem_cgroup_tree_per_node *mctz) +/* + * mem_cgroup_flush_stats - flush the stats of a memory cgroup subtree + * @memcg: root of the subtree to flush + * + * Flushing is serialized by the underlying global rstat lock. There is also a + * minimum amount of work to be done even if there are no stat updates to flush. + * Hence, we only flush the stats if the updates delta exceeds a threshold. This + * avoids unnecessary work and contention on the underlying lock. + */ +void mem_cgroup_flush_stats(struct mem_cgroup *memcg) { - if (!mz->on_tree) + if (mem_cgroup_disabled()) return; - if (&mz->tree_node == mctz->rb_rightmost) - mctz->rb_rightmost = rb_prev(&mz->tree_node); + if (!memcg) + memcg = root_mem_cgroup; - rb_erase(&mz->tree_node, &mctz->rb_root); - mz->on_tree = false; + __mem_cgroup_flush_stats(memcg, false); } -static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz, - struct mem_cgroup_tree_per_node *mctz) +void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg) { - unsigned long flags; + /* Only flush if the periodic flusher is one full cycle late */ + if (time_after64(jiffies_64, READ_ONCE(flush_last_time) + 2*FLUSH_TIME)) + mem_cgroup_flush_stats(memcg); +} - spin_lock_irqsave(&mctz->lock, flags); - __mem_cgroup_remove_exceeded(mz, mctz); - spin_unlock_irqrestore(&mctz->lock, flags); +static void flush_memcg_stats_dwork(struct work_struct *w) +{ + /* + * Deliberately ignore memcg_vmstats_needs_flush() here so that flushing + * in latency-sensitive paths is as cheap as possible. + */ + __mem_cgroup_flush_stats(root_mem_cgroup, true); + queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME); } -static unsigned long soft_limit_excess(struct mem_cgroup *memcg) +unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { - unsigned long nr_pages = page_counter_read(&memcg->memory); - unsigned long soft_limit = READ_ONCE(memcg->soft_limit); - unsigned long excess = 0; + long x; + int i = memcg_stats_index(idx); - if (nr_pages > soft_limit) - excess = nr_pages - soft_limit; + if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx)) + return 0; - return excess; + x = READ_ONCE(memcg->vmstats->state[i]); +#ifdef CONFIG_SMP + if (x < 0) + x = 0; +#endif + return x; } -static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) +static int memcg_page_state_unit(int item); + +/* + * Normalize the value passed into memcg_rstat_updated() to be in pages. Round + * up non-zero sub-page updates to 1 page as zero page updates are ignored. + */ +static int memcg_state_val_in_pages(int idx, int val) { - unsigned long excess; - struct mem_cgroup_per_node *mz; - struct mem_cgroup_tree_per_node *mctz; + int unit = memcg_page_state_unit(idx); + + if (!val || unit == PAGE_SIZE) + return val; + else + return max(val * unit / PAGE_SIZE, 1UL); +} + +/** + * mod_memcg_state - update cgroup memory statistics + * @memcg: the memory cgroup + * @idx: the stat item - can be enum memcg_stat_item or enum node_stat_item + * @val: delta to add to the counter, can be negative + */ +void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, + int val) +{ + int i = memcg_stats_index(idx); + int cpu; - mctz = soft_limit_tree_from_page(page); - if (!mctz) + if (mem_cgroup_disabled()) return; - /* - * Necessary to update all ancestors when hierarchy is used. - * because their event counter is not touched. - */ - for (; memcg; memcg = parent_mem_cgroup(memcg)) { - mz = mem_cgroup_page_nodeinfo(memcg, page); - excess = soft_limit_excess(memcg); - /* - * We have to update the tree if mz is on RB-tree or - * mem is over its softlimit. - */ - if (excess || mz->on_tree) { - unsigned long flags; - spin_lock_irqsave(&mctz->lock, flags); - /* if on-tree, remove it */ - if (mz->on_tree) - __mem_cgroup_remove_exceeded(mz, mctz); - /* - * Insert again. mz->usage_in_excess will be updated. - * If excess is 0, no tree ops. - */ - __mem_cgroup_insert_exceeded(mz, mctz, excess); - spin_unlock_irqrestore(&mctz->lock, flags); - } - } + if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx)) + return; + + cpu = get_cpu(); + + this_cpu_add(memcg->vmstats_percpu->state[i], val); + val = memcg_state_val_in_pages(idx, val); + memcg_rstat_updated(memcg, val, cpu); + trace_mod_memcg_state(memcg, idx, val); + + put_cpu(); } -static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) +#ifdef CONFIG_MEMCG_V1 +/* idx can be of type enum memcg_stat_item or node_stat_item. */ +unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx) { - struct mem_cgroup_tree_per_node *mctz; - struct mem_cgroup_per_node *mz; - int nid; + long x; + int i = memcg_stats_index(idx); - for_each_node(nid) { - mz = mem_cgroup_nodeinfo(memcg, nid); - mctz = soft_limit_tree_node(nid); - if (mctz) - mem_cgroup_remove_exceeded(mz, mctz); - } + if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx)) + return 0; + + x = READ_ONCE(memcg->vmstats->state_local[i]); +#ifdef CONFIG_SMP + if (x < 0) + x = 0; +#endif + return x; } +#endif -static struct mem_cgroup_per_node * -__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz) +static void mod_memcg_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx, + int val) { - struct mem_cgroup_per_node *mz; + struct mem_cgroup_per_node *pn; + struct mem_cgroup *memcg; + int i = memcg_stats_index(idx); + int cpu; -retry: - mz = NULL; - if (!mctz->rb_rightmost) - goto done; /* Nothing to reclaim from */ + if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx)) + return; - mz = rb_entry(mctz->rb_rightmost, - struct mem_cgroup_per_node, tree_node); - /* - * Remove the node now but someone else can add it back, - * we will to add it back at the end of reclaim to its correct - * position in the tree. - */ - __mem_cgroup_remove_exceeded(mz, mctz); - if (!soft_limit_excess(mz->memcg) || - !css_tryget_online(&mz->memcg->css)) - goto retry; -done: - return mz; + pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); + memcg = pn->memcg; + + cpu = get_cpu(); + + /* Update memcg */ + this_cpu_add(memcg->vmstats_percpu->state[i], val); + + /* Update lruvec */ + this_cpu_add(pn->lruvec_stats_percpu->state[i], val); + + val = memcg_state_val_in_pages(idx, val); + memcg_rstat_updated(memcg, val, cpu); + trace_mod_memcg_lruvec_state(memcg, idx, val); + + put_cpu(); } -static struct mem_cgroup_per_node * -mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz) +/** + * mod_lruvec_state - update lruvec memory statistics + * @lruvec: the lruvec + * @idx: the stat item + * @val: delta to add to the counter, can be negative + * + * The lruvec is the intersection of the NUMA node and a cgroup. This + * function updates the all three counters that are affected by a + * change of state at this level: per-node, per-cgroup, per-lruvec. + */ +void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, + int val) { - struct mem_cgroup_per_node *mz; + /* Update node */ + mod_node_page_state(lruvec_pgdat(lruvec), idx, val); - spin_lock_irq(&mctz->lock); - mz = __mem_cgroup_largest_soft_limit_node(mctz); - spin_unlock_irq(&mctz->lock); - return mz; + /* Update memcg and lruvec */ + if (!mem_cgroup_disabled()) + mod_memcg_lruvec_state(lruvec, idx, val); } -static unsigned long memcg_sum_events(struct mem_cgroup *memcg, - int event) +void lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, + int val) { - return atomic_long_read(&memcg->events[event]); + struct mem_cgroup *memcg; + pg_data_t *pgdat = folio_pgdat(folio); + struct lruvec *lruvec; + + rcu_read_lock(); + memcg = folio_memcg(folio); + /* Untracked pages have no memcg, no lruvec. Update only the node */ + if (!memcg) { + rcu_read_unlock(); + mod_node_page_state(pgdat, idx, val); + return; + } + + lruvec = mem_cgroup_lruvec(memcg, pgdat); + mod_lruvec_state(lruvec, idx, val); + rcu_read_unlock(); } +EXPORT_SYMBOL(lruvec_stat_mod_folio); -static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, - struct page *page, - bool compound, int nr_pages) +void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { + pg_data_t *pgdat = page_pgdat(virt_to_page(p)); + struct mem_cgroup *memcg; + struct lruvec *lruvec; + + rcu_read_lock(); + memcg = mem_cgroup_from_slab_obj(p); + /* - * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is - * counted as CACHE even if it's on ANON LRU. + * Untracked pages have no memcg, no lruvec. Update only the + * node. If we reparent the slab objects to the root memcg, + * when we free the slab object, we need to update the per-memcg + * vmstats to keep it correct for the root memcg. */ - if (PageAnon(page)) - __mod_memcg_state(memcg, MEMCG_RSS, nr_pages); - else { - __mod_memcg_state(memcg, MEMCG_CACHE, nr_pages); - if (PageSwapBacked(page)) - __mod_memcg_state(memcg, NR_SHMEM, nr_pages); + if (!memcg) { + mod_node_page_state(pgdat, idx, val); + } else { + lruvec = mem_cgroup_lruvec(memcg, pgdat); + mod_lruvec_state(lruvec, idx, val); } + rcu_read_unlock(); +} - if (compound) { - VM_BUG_ON_PAGE(!PageTransHuge(page), page); - __mod_memcg_state(memcg, MEMCG_RSS_HUGE, nr_pages); - } +/** + * count_memcg_events - account VM events in a cgroup + * @memcg: the memory cgroup + * @idx: the event item + * @count: the number of events that occurred + */ +void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, + unsigned long count) +{ + int i = memcg_events_index(idx); + int cpu; - /* pagein of a big page is an event. So, ignore page size */ - if (nr_pages > 0) - __count_memcg_events(memcg, PGPGIN, 1); - else { - __count_memcg_events(memcg, PGPGOUT, 1); - nr_pages = -nr_pages; /* for event */ - } + if (mem_cgroup_disabled()) + return; - __this_cpu_add(memcg->stat_cpu->nr_page_events, nr_pages); -} + if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx)) + return; -unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, - int nid, unsigned int lru_mask) -{ - struct lruvec *lruvec = mem_cgroup_lruvec(NODE_DATA(nid), memcg); - unsigned long nr = 0; - enum lru_list lru; + cpu = get_cpu(); - VM_BUG_ON((unsigned)nid >= nr_node_ids); + this_cpu_add(memcg->vmstats_percpu->events[i], count); + memcg_rstat_updated(memcg, count, cpu); + trace_count_memcg_events(memcg, idx, count); - for_each_lru(lru) { - if (!(BIT(lru) & lru_mask)) - continue; - nr += mem_cgroup_get_lru_size(lruvec, lru); - } - return nr; + put_cpu(); } -static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg, - unsigned int lru_mask) +unsigned long memcg_events(struct mem_cgroup *memcg, int event) { - unsigned long nr = 0; - int nid; + int i = memcg_events_index(event); + + if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, event)) + return 0; - for_each_node_state(nid, N_MEMORY) - nr += mem_cgroup_node_nr_lru_pages(memcg, nid, lru_mask); - return nr; + return READ_ONCE(memcg->vmstats->events[i]); } -static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, - enum mem_cgroup_events_target target) +#ifdef CONFIG_MEMCG_V1 +unsigned long memcg_events_local(struct mem_cgroup *memcg, int event) { - unsigned long val, next; + int i = memcg_events_index(event); - val = __this_cpu_read(memcg->stat_cpu->nr_page_events); - next = __this_cpu_read(memcg->stat_cpu->targets[target]); - /* from time_after() in jiffies.h */ - if ((long)(next - val) < 0) { - switch (target) { - case MEM_CGROUP_TARGET_THRESH: - next = val + THRESHOLDS_EVENTS_TARGET; - break; - case MEM_CGROUP_TARGET_SOFTLIMIT: - next = val + SOFTLIMIT_EVENTS_TARGET; - break; - case MEM_CGROUP_TARGET_NUMAINFO: - next = val + NUMAINFO_EVENTS_TARGET; - break; - default: - break; - } - __this_cpu_write(memcg->stat_cpu->targets[target], next); - return true; - } - return false; -} + if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, event)) + return 0; -/* - * Check events in order. - * - */ -static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) -{ - /* threshold event is triggered in finer grain than soft limit */ - if (unlikely(mem_cgroup_event_ratelimit(memcg, - MEM_CGROUP_TARGET_THRESH))) { - bool do_softlimit; - bool do_numainfo __maybe_unused; - - do_softlimit = mem_cgroup_event_ratelimit(memcg, - MEM_CGROUP_TARGET_SOFTLIMIT); -#if MAX_NUMNODES > 1 - do_numainfo = mem_cgroup_event_ratelimit(memcg, - MEM_CGROUP_TARGET_NUMAINFO); -#endif - mem_cgroup_threshold(memcg); - if (unlikely(do_softlimit)) - mem_cgroup_update_tree(memcg, page); -#if MAX_NUMNODES > 1 - if (unlikely(do_numainfo)) - atomic_inc(&memcg->numainfo_events); -#endif - } + return READ_ONCE(memcg->vmstats->events_local[i]); } +#endif struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) { @@ -816,13 +886,24 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) } EXPORT_SYMBOL(mem_cgroup_from_task); +static __always_inline struct mem_cgroup *active_memcg(void) +{ + if (!in_task()) + return this_cpu_read(int_active_memcg); + else + return current->active_memcg; +} + /** * get_mem_cgroup_from_mm: Obtain a reference on given mm_struct's memcg. * @mm: mm from which memcg should be extracted. It can be NULL. * - * Obtain a reference on mm->memcg and returns it if successful. Otherwise - * root_mem_cgroup is returned. However if mem_cgroup is disabled, NULL is - * returned. + * Obtain a reference on mm->memcg and returns it if successful. If mm + * is NULL, then the memcg is chosen as follows: + * 1) The active memcg, if set. + * 2) current->mm->memcg, if available + * 3) root memcg + * If mem_cgroup is disabled, NULL is returned. */ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { @@ -831,63 +912,75 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) if (mem_cgroup_disabled()) return NULL; + /* + * Page cache insertions can happen without an + * actual mm context, e.g. during disk probing + * on boot, loopback IO, acct() writes etc. + * + * No need to css_get on root memcg as the reference + * counting is disabled on the root level in the + * cgroup core. See CSS_NO_REF. + */ + if (unlikely(!mm)) { + memcg = active_memcg(); + if (unlikely(memcg)) { + /* remote memcg must hold a ref */ + css_get(&memcg->css); + return memcg; + } + mm = current->mm; + if (unlikely(!mm)) + return root_mem_cgroup; + } + rcu_read_lock(); do { - /* - * Page cache insertions can happen withou an - * actual mm context, e.g. during disk probing - * on boot, loopback IO, acct() writes etc. - */ - if (unlikely(!mm)) + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (unlikely(!memcg)) memcg = root_mem_cgroup; - else { - memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); - if (unlikely(!memcg)) - memcg = root_mem_cgroup; - } - } while (!css_tryget_online(&memcg->css)); + } while (!css_tryget(&memcg->css)); rcu_read_unlock(); return memcg; } EXPORT_SYMBOL(get_mem_cgroup_from_mm); /** - * get_mem_cgroup_from_page: Obtain a reference on given page's memcg. - * @page: page from which memcg should be extracted. - * - * Obtain a reference on page->memcg and returns it if successful. Otherwise - * root_mem_cgroup is returned. + * get_mem_cgroup_from_current - Obtain a reference on current task's memcg. */ -struct mem_cgroup *get_mem_cgroup_from_page(struct page *page) +struct mem_cgroup *get_mem_cgroup_from_current(void) { - struct mem_cgroup *memcg = page->mem_cgroup; + struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return NULL; +again: rcu_read_lock(); - if (!memcg || !css_tryget_online(&memcg->css)) - memcg = root_mem_cgroup; + memcg = mem_cgroup_from_task(current); + if (!css_tryget(&memcg->css)) { + rcu_read_unlock(); + goto again; + } rcu_read_unlock(); return memcg; } -EXPORT_SYMBOL(get_mem_cgroup_from_page); /** - * If current->active_memcg is non-NULL, do not fallback to current->mm->memcg. + * get_mem_cgroup_from_folio - Obtain a reference on a given folio's memcg. + * @folio: folio from which memcg should be extracted. */ -static __always_inline struct mem_cgroup *get_mem_cgroup_from_current(void) +struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio) { - if (unlikely(current->active_memcg)) { - struct mem_cgroup *memcg = root_mem_cgroup; + struct mem_cgroup *memcg = folio_memcg(folio); - rcu_read_lock(); - if (css_tryget_online(¤t->active_memcg->css)) - memcg = current->active_memcg; - rcu_read_unlock(); - return memcg; - } - return get_mem_cgroup_from_mm(current->mm); + if (mem_cgroup_disabled()) + return NULL; + + rcu_read_lock(); + if (!memcg || WARN_ON_ONCE(!css_tryget(&memcg->css))) + memcg = root_mem_cgroup; + rcu_read_unlock(); + return memcg; } /** @@ -903,18 +996,18 @@ static __always_inline struct mem_cgroup *get_mem_cgroup_from_current(void) * invocations for reference counting, or use mem_cgroup_iter_break() * to cancel a hierarchy walk before the round-trip is complete. * - * Reclaimers can specify a node and a priority level in @reclaim to - * divide up the memcgs in the hierarchy among all concurrent - * reclaimers operating on the same node and priority. + * Reclaimers can specify a node in @reclaim to divide up the memcgs + * in the hierarchy among all concurrent reclaimers operating on the + * same node. */ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, struct mem_cgroup_reclaim_cookie *reclaim) { - struct mem_cgroup_reclaim_iter *uninitialized_var(iter); - struct cgroup_subsys_state *css = NULL; - struct mem_cgroup *memcg = NULL; - struct mem_cgroup *pos = NULL; + struct mem_cgroup_reclaim_iter *iter; + struct cgroup_subsys_state *css; + struct mem_cgroup *pos; + struct mem_cgroup *next; if (mem_cgroup_disabled()) return NULL; @@ -922,99 +1015,76 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, if (!root) root = root_mem_cgroup; - if (prev && !reclaim) - pos = prev; - - if (!root->use_hierarchy && root != root_mem_cgroup) { - if (prev) - goto out; - return root; - } - rcu_read_lock(); +restart: + next = NULL; if (reclaim) { - struct mem_cgroup_per_node *mz; + int gen; + int nid = reclaim->pgdat->node_id; - mz = mem_cgroup_nodeinfo(root, reclaim->pgdat->node_id); - iter = &mz->iter[reclaim->priority]; + iter = &root->nodeinfo[nid]->iter; + gen = atomic_read(&iter->generation); - if (prev && reclaim->generation != iter->generation) + /* + * On start, join the current reclaim iteration cycle. + * Exit when a concurrent walker completes it. + */ + if (!prev) + reclaim->generation = gen; + else if (reclaim->generation != gen) goto out_unlock; - while (1) { - pos = READ_ONCE(iter->position); - if (!pos || css_tryget(&pos->css)) - break; - /* - * css reference reached zero, so iter->position will - * be cleared by ->css_released. However, we should not - * rely on this happening soon, because ->css_released - * is called from a work queue, and by busy-waiting we - * might block it. So we clear iter->position right - * away. - */ - (void)cmpxchg(&iter->position, pos, NULL); - } - } - - if (pos) - css = &pos->css; + pos = READ_ONCE(iter->position); + } else + pos = prev; - for (;;) { - css = css_next_descendant_pre(css, &root->css); - if (!css) { - /* - * Reclaimers share the hierarchy walk, and a - * new one might jump in right at the end of - * the hierarchy - make sure they see at least - * one group and restart from the beginning. - */ - if (!prev) - continue; - break; - } + css = pos ? &pos->css : NULL; + while ((css = css_next_descendant_pre(css, &root->css))) { /* * Verify the css and acquire a reference. The root * is provided by the caller, so we know it's alive * and kicking, and don't take an extra reference. */ - memcg = mem_cgroup_from_css(css); - - if (css == &root->css) - break; - - if (css_tryget(css)) + if (css == &root->css || css_tryget(css)) break; - - memcg = NULL; } + next = mem_cgroup_from_css(css); + if (reclaim) { /* * The position could have already been updated by a competing * thread, so check that the value hasn't changed since we read * it to avoid reclaiming from the same cgroup twice. */ - (void)cmpxchg(&iter->position, pos, memcg); + if (cmpxchg(&iter->position, pos, next) != pos) { + if (css && css != &root->css) + css_put(css); + goto restart; + } - if (pos) - css_put(&pos->css); + if (!next) { + atomic_inc(&iter->generation); - if (!memcg) - iter->generation++; - else if (!prev) - reclaim->generation = iter->generation; + /* + * Reclaimers share the hierarchy walk, and a + * new one might jump in right at the end of + * the hierarchy - make sure they see at least + * one group and restart from the beginning. + */ + if (!prev) + goto restart; + } } out_unlock: rcu_read_unlock(); -out: if (prev && prev != root) css_put(&prev->css); - return memcg; + return next; } /** @@ -1031,26 +1101,41 @@ void mem_cgroup_iter_break(struct mem_cgroup *root, css_put(&prev->css); } -static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) +static void __invalidate_reclaim_iterators(struct mem_cgroup *from, + struct mem_cgroup *dead_memcg) { - struct mem_cgroup *memcg = dead_memcg; struct mem_cgroup_reclaim_iter *iter; struct mem_cgroup_per_node *mz; int nid; - int i; - for (; memcg; memcg = parent_mem_cgroup(memcg)) { - for_each_node(nid) { - mz = mem_cgroup_nodeinfo(memcg, nid); - for (i = 0; i <= DEF_PRIORITY; i++) { - iter = &mz->iter[i]; - cmpxchg(&iter->position, - dead_memcg, NULL); - } - } + for_each_node(nid) { + mz = from->nodeinfo[nid]; + iter = &mz->iter; + cmpxchg(&iter->position, dead_memcg, NULL); } } +static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) +{ + struct mem_cgroup *memcg = dead_memcg; + struct mem_cgroup *last; + + do { + __invalidate_reclaim_iterators(memcg, dead_memcg); + last = memcg; + } while ((memcg = parent_mem_cgroup(memcg))); + + /* + * When cgroup1 non-hierarchy mode is used, + * parent_mem_cgroup() does not walk all the way up to the + * cgroup root (root_mem_cgroup). So we have to handle + * dead_memcg from cgroup root separately. + */ + if (!mem_cgroup_is_root(last)) + __invalidate_reclaim_iterators(root_mem_cgroup, + dead_memcg); +} + /** * mem_cgroup_scan_tasks - iterate over tasks of a memory cgroup hierarchy * @memcg: hierarchy root @@ -1059,73 +1144,118 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) * * This function iterates over tasks attached to @memcg or to any of its * descendants and calls @fn for each task. If @fn returns a non-zero - * value, the function breaks the iteration loop and returns the value. - * Otherwise, it will iterate over all tasks and return 0. + * value, the function breaks the iteration loop. Otherwise, it will iterate + * over all tasks and return 0. * * This function must not be called for the root memory cgroup. */ -int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, - int (*fn)(struct task_struct *, void *), void *arg) +void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, + int (*fn)(struct task_struct *, void *), void *arg) { struct mem_cgroup *iter; int ret = 0; - BUG_ON(memcg == root_mem_cgroup); + BUG_ON(mem_cgroup_is_root(memcg)); for_each_mem_cgroup_tree(iter, memcg) { struct css_task_iter it; struct task_struct *task; - css_task_iter_start(&iter->css, 0, &it); - while (!ret && (task = css_task_iter_next(&it))) + css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it); + while (!ret && (task = css_task_iter_next(&it))) { ret = fn(task, arg); + /* Avoid potential softlockup warning */ + cond_resched(); + } css_task_iter_end(&it); if (ret) { mem_cgroup_iter_break(memcg, iter); break; } } - return ret; } +#ifdef CONFIG_DEBUG_VM +void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) +{ + struct mem_cgroup *memcg; + + if (mem_cgroup_disabled()) + return; + + memcg = folio_memcg(folio); + + if (!memcg) + VM_BUG_ON_FOLIO(!mem_cgroup_is_root(lruvec_memcg(lruvec)), folio); + else + VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != memcg, folio); +} +#endif + /** - * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page - * @page: the page - * @pgdat: pgdat of the page + * folio_lruvec_lock - Lock the lruvec for a folio. + * @folio: Pointer to the folio. + * + * These functions are safe to use under any of the following conditions: + * - folio locked + * - folio_test_lru false + * - folio frozen (refcount of 0) * - * This function is only safe when following the LRU page isolation - * and putback protocol: the LRU lock must be held, and the page must - * either be PageLRU() or the caller must have isolated/allocated it. + * Return: The lruvec this folio is on with its lock held. */ -struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat) +struct lruvec *folio_lruvec_lock(struct folio *folio) { - struct mem_cgroup_per_node *mz; - struct mem_cgroup *memcg; - struct lruvec *lruvec; + struct lruvec *lruvec = folio_lruvec(folio); - if (mem_cgroup_disabled()) { - lruvec = &pgdat->lruvec; - goto out; - } + spin_lock(&lruvec->lru_lock); + lruvec_memcg_debug(lruvec, folio); - memcg = page->mem_cgroup; - /* - * Swapcache readahead pages are added to the LRU - and - * possibly migrated - before they are charged. - */ - if (!memcg) - memcg = root_mem_cgroup; + return lruvec; +} + +/** + * folio_lruvec_lock_irq - Lock the lruvec for a folio. + * @folio: Pointer to the folio. + * + * These functions are safe to use under any of the following conditions: + * - folio locked + * - folio_test_lru false + * - folio frozen (refcount of 0) + * + * Return: The lruvec this folio is on with its lock held and interrupts + * disabled. + */ +struct lruvec *folio_lruvec_lock_irq(struct folio *folio) +{ + struct lruvec *lruvec = folio_lruvec(folio); + + spin_lock_irq(&lruvec->lru_lock); + lruvec_memcg_debug(lruvec, folio); + + return lruvec; +} + +/** + * folio_lruvec_lock_irqsave - Lock the lruvec for a folio. + * @folio: Pointer to the folio. + * @flags: Pointer to irqsave flags. + * + * These functions are safe to use under any of the following conditions: + * - folio locked + * - folio_test_lru false + * - folio frozen (refcount of 0) + * + * Return: The lruvec this folio is on with its lock held and interrupts + * disabled. + */ +struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, + unsigned long *flags) +{ + struct lruvec *lruvec = folio_lruvec(folio); + + spin_lock_irqsave(&lruvec->lru_lock, *flags); + lruvec_memcg_debug(lruvec, folio); - mz = mem_cgroup_page_nodeinfo(memcg, page); - lruvec = &mz->lruvec; -out: - /* - * Since a node can be onlined after the mem_cgroup was created, - * we have to be prepared to initialize lruvec->zone here; - * and if offlined then reonlined, we need to reinitialize it. - */ - if (unlikely(lruvec->pgdat != pgdat)) - lruvec->pgdat = pgdat; return lruvec; } @@ -1137,8 +1267,7 @@ out: * @nr_pages: positive when adding or negative when removing * * This function must be called under lru_lock, just before a page is added - * to or just after a page is removed from an lru list (that ordering being - * so as to allow it to check that lru_size 0 is consistent with list_empty). + * to or just after a page is removed from an lru list. */ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int zid, int nr_pages) @@ -1168,32 +1297,6 @@ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, *lru_size += nr_pages; } -bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg) -{ - struct mem_cgroup *task_memcg; - struct task_struct *p; - bool ret; - - p = find_lock_task_mm(task); - if (p) { - task_memcg = get_mem_cgroup_from_mm(p->mm); - task_unlock(p); - } else { - /* - * All threads may have already detached their mm's, but the oom - * killer still needs to detect if they have already been oom - * killed to prevent needlessly killing additional tasks. - */ - rcu_read_lock(); - task_memcg = mem_cgroup_from_task(task); - css_get(&task_memcg->css); - rcu_read_unlock(); - } - ret = mem_cgroup_is_descendant(task_memcg, memcg); - css_put(&task_memcg->css); - return ret; -} - /** * mem_cgroup_margin - calculate chargeable space of a memory cgroup * @memcg: the memory cgroup @@ -1215,7 +1318,7 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) if (do_memsw_account()) { count = page_counter_read(&memcg->memsw); limit = READ_ONCE(memcg->memsw.max); - if (count <= limit) + if (count < limit) margin = min(margin, limit - count); else margin = 0; @@ -1224,74 +1327,207 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) return margin; } -/* - * A routine for checking "mem" is under move_account() or not. - * - * Checking a cgroup is mc.from or mc.to or under hierarchy of - * moving cgroups. This is for waiting at high-memory pressure - * caused by "move". - */ -static bool mem_cgroup_under_move(struct mem_cgroup *memcg) +struct memory_stat { + const char *name; + unsigned int idx; +}; + +static const struct memory_stat memory_stats[] = { + { "anon", NR_ANON_MAPPED }, + { "file", NR_FILE_PAGES }, + { "kernel", MEMCG_KMEM }, + { "kernel_stack", NR_KERNEL_STACK_KB }, + { "pagetables", NR_PAGETABLE }, + { "sec_pagetables", NR_SECONDARY_PAGETABLE }, + { "percpu", MEMCG_PERCPU_B }, + { "sock", MEMCG_SOCK }, + { "vmalloc", MEMCG_VMALLOC }, + { "shmem", NR_SHMEM }, +#ifdef CONFIG_ZSWAP + { "zswap", MEMCG_ZSWAP_B }, + { "zswapped", MEMCG_ZSWAPPED }, +#endif + { "file_mapped", NR_FILE_MAPPED }, + { "file_dirty", NR_FILE_DIRTY }, + { "file_writeback", NR_WRITEBACK }, +#ifdef CONFIG_SWAP + { "swapcached", NR_SWAPCACHE }, +#endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + { "anon_thp", NR_ANON_THPS }, + { "file_thp", NR_FILE_THPS }, + { "shmem_thp", NR_SHMEM_THPS }, +#endif + { "inactive_anon", NR_INACTIVE_ANON }, + { "active_anon", NR_ACTIVE_ANON }, + { "inactive_file", NR_INACTIVE_FILE }, + { "active_file", NR_ACTIVE_FILE }, + { "unevictable", NR_UNEVICTABLE }, + { "slab_reclaimable", NR_SLAB_RECLAIMABLE_B }, + { "slab_unreclaimable", NR_SLAB_UNRECLAIMABLE_B }, +#ifdef CONFIG_HUGETLB_PAGE + { "hugetlb", NR_HUGETLB }, +#endif + + /* The memory events */ + { "workingset_refault_anon", WORKINGSET_REFAULT_ANON }, + { "workingset_refault_file", WORKINGSET_REFAULT_FILE }, + { "workingset_activate_anon", WORKINGSET_ACTIVATE_ANON }, + { "workingset_activate_file", WORKINGSET_ACTIVATE_FILE }, + { "workingset_restore_anon", WORKINGSET_RESTORE_ANON }, + { "workingset_restore_file", WORKINGSET_RESTORE_FILE }, + { "workingset_nodereclaim", WORKINGSET_NODERECLAIM }, + + { "pgdemote_kswapd", PGDEMOTE_KSWAPD }, + { "pgdemote_direct", PGDEMOTE_DIRECT }, + { "pgdemote_khugepaged", PGDEMOTE_KHUGEPAGED }, + { "pgdemote_proactive", PGDEMOTE_PROACTIVE }, +#ifdef CONFIG_NUMA_BALANCING + { "pgpromote_success", PGPROMOTE_SUCCESS }, +#endif +}; + +/* The actual unit of the state item, not the same as the output unit */ +static int memcg_page_state_unit(int item) +{ + switch (item) { + case MEMCG_PERCPU_B: + case MEMCG_ZSWAP_B: + case NR_SLAB_RECLAIMABLE_B: + case NR_SLAB_UNRECLAIMABLE_B: + return 1; + case NR_KERNEL_STACK_KB: + return SZ_1K; + default: + return PAGE_SIZE; + } +} + +/* Translate stat items to the correct unit for memory.stat output */ +static int memcg_page_state_output_unit(int item) { - struct mem_cgroup *from; - struct mem_cgroup *to; - bool ret = false; /* - * Unlike task_move routines, we access mc.to, mc.from not under - * mutual exclusion by cgroup_mutex. Here, we take spinlock instead. + * Workingset state is actually in pages, but we export it to userspace + * as a scalar count of events, so special case it here. + * + * Demotion and promotion activities are exported in pages, consistent + * with their global counterparts. */ - spin_lock(&mc.lock); - from = mc.from; - to = mc.to; - if (!from) - goto unlock; + switch (item) { + case WORKINGSET_REFAULT_ANON: + case WORKINGSET_REFAULT_FILE: + case WORKINGSET_ACTIVATE_ANON: + case WORKINGSET_ACTIVATE_FILE: + case WORKINGSET_RESTORE_ANON: + case WORKINGSET_RESTORE_FILE: + case WORKINGSET_NODERECLAIM: + case PGDEMOTE_KSWAPD: + case PGDEMOTE_DIRECT: + case PGDEMOTE_KHUGEPAGED: + case PGDEMOTE_PROACTIVE: +#ifdef CONFIG_NUMA_BALANCING + case PGPROMOTE_SUCCESS: +#endif + return 1; + default: + return memcg_page_state_unit(item); + } +} - ret = mem_cgroup_is_descendant(from, memcg) || - mem_cgroup_is_descendant(to, memcg); -unlock: - spin_unlock(&mc.lock); - return ret; +unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item) +{ + return memcg_page_state(memcg, item) * + memcg_page_state_output_unit(item); } -static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg) +#ifdef CONFIG_MEMCG_V1 +unsigned long memcg_page_state_local_output(struct mem_cgroup *memcg, int item) +{ + return memcg_page_state_local(memcg, item) * + memcg_page_state_output_unit(item); +} +#endif + +#ifdef CONFIG_HUGETLB_PAGE +static bool memcg_accounts_hugetlb(void) +{ + return cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; +} +#else /* CONFIG_HUGETLB_PAGE */ +static bool memcg_accounts_hugetlb(void) { - if (mc.moving_task && current != mc.moving_task) { - if (mem_cgroup_under_move(memcg)) { - DEFINE_WAIT(wait); - prepare_to_wait(&mc.waitq, &wait, TASK_INTERRUPTIBLE); - /* moving charge context might have finished. */ - if (mc.moving_task) - schedule(); - finish_wait(&mc.waitq, &wait); - return true; - } - } return false; } +#endif /* CONFIG_HUGETLB_PAGE */ -static const unsigned int memcg1_stats[] = { - MEMCG_CACHE, - MEMCG_RSS, - MEMCG_RSS_HUGE, - NR_SHMEM, - NR_FILE_MAPPED, - NR_FILE_DIRTY, - NR_WRITEBACK, - MEMCG_SWAP, -}; +static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s) +{ + int i; -static const char *const memcg1_stat_names[] = { - "cache", - "rss", - "rss_huge", - "shmem", - "mapped_file", - "dirty", - "writeback", - "swap", -}; + /* + * Provide statistics on the state of the memory subsystem as + * well as cumulative event counters that show past behavior. + * + * This list is ordered following a combination of these gradients: + * 1) generic big picture -> specifics and details + * 2) reflecting userspace activity -> reflecting kernel heuristics + * + * Current memory state: + */ + mem_cgroup_flush_stats(memcg); + + for (i = 0; i < ARRAY_SIZE(memory_stats); i++) { + u64 size; + +#ifdef CONFIG_HUGETLB_PAGE + if (unlikely(memory_stats[i].idx == NR_HUGETLB) && + !memcg_accounts_hugetlb()) + continue; +#endif + size = memcg_page_state_output(memcg, memory_stats[i].idx); + seq_buf_printf(s, "%s %llu\n", memory_stats[i].name, size); + + if (unlikely(memory_stats[i].idx == NR_SLAB_UNRECLAIMABLE_B)) { + size += memcg_page_state_output(memcg, + NR_SLAB_RECLAIMABLE_B); + seq_buf_printf(s, "slab %llu\n", size); + } + } + + /* Accumulated memory events */ + seq_buf_printf(s, "pgscan %lu\n", + memcg_events(memcg, PGSCAN_KSWAPD) + + memcg_events(memcg, PGSCAN_DIRECT) + + memcg_events(memcg, PGSCAN_PROACTIVE) + + memcg_events(memcg, PGSCAN_KHUGEPAGED)); + seq_buf_printf(s, "pgsteal %lu\n", + memcg_events(memcg, PGSTEAL_KSWAPD) + + memcg_events(memcg, PGSTEAL_DIRECT) + + memcg_events(memcg, PGSTEAL_PROACTIVE) + + memcg_events(memcg, PGSTEAL_KHUGEPAGED)); + + for (i = 0; i < ARRAY_SIZE(memcg_vm_event_stat); i++) { +#ifdef CONFIG_MEMCG_V1 + if (memcg_vm_event_stat[i] == PGPGIN || + memcg_vm_event_stat[i] == PGPGOUT) + continue; +#endif + seq_buf_printf(s, "%s %lu\n", + vm_event_name(memcg_vm_event_stat[i]), + memcg_events(memcg, memcg_vm_event_stat[i])); + } +} + +static void memory_stat_format(struct mem_cgroup *memcg, struct seq_buf *s) +{ + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + memcg_stat_format(memcg, s); + else + memcg1_stat_format(memcg, s); + if (seq_buf_has_overflowed(s)) + pr_warn("%s: Warning, stat buffer overflow, please report\n", __func__); +} -#define K(x) ((x) << (PAGE_SHIFT-10)) /** * mem_cgroup_print_oom_context: Print OOM information relevant to * memory controller. @@ -1324,37 +1560,43 @@ void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct * */ void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { - struct mem_cgroup *iter; - unsigned int i; - - pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n", - K((u64)page_counter_read(&memcg->memory)), - K((u64)memcg->memory.max), memcg->memory.failcnt); - pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n", - K((u64)page_counter_read(&memcg->memsw)), - K((u64)memcg->memsw.max), memcg->memsw.failcnt); - pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n", - K((u64)page_counter_read(&memcg->kmem)), - K((u64)memcg->kmem.max), memcg->kmem.failcnt); + /* Use static buffer, for the caller is holding oom_lock. */ + static char buf[SEQ_BUF_SIZE]; + struct seq_buf s; + unsigned long memory_failcnt; - for_each_mem_cgroup_tree(iter, memcg) { - pr_info("Memory cgroup stats for "); - pr_cont_cgroup_path(iter->css.cgroup); - pr_cont(":"); - - for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { - if (memcg1_stats[i] == MEMCG_SWAP && !do_swap_account) - continue; - pr_cont(" %s:%luKB", memcg1_stat_names[i], - K(memcg_page_state(iter, memcg1_stats[i]))); - } + lockdep_assert_held(&oom_lock); - for (i = 0; i < NR_LRU_LISTS; i++) - pr_cont(" %s:%luKB", mem_cgroup_lru_names[i], - K(mem_cgroup_nr_lru_pages(iter, BIT(i)))); + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + memory_failcnt = atomic_long_read(&memcg->memory_events[MEMCG_MAX]); + else + memory_failcnt = memcg->memory.failcnt; - pr_cont("\n"); + pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n", + K((u64)page_counter_read(&memcg->memory)), + K((u64)READ_ONCE(memcg->memory.max)), memory_failcnt); + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + pr_info("swap: usage %llukB, limit %llukB, failcnt %lu\n", + K((u64)page_counter_read(&memcg->swap)), + K((u64)READ_ONCE(memcg->swap.max)), + atomic_long_read(&memcg->memory_events[MEMCG_SWAP_MAX])); +#ifdef CONFIG_MEMCG_V1 + else { + pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n", + K((u64)page_counter_read(&memcg->memsw)), + K((u64)memcg->memsw.max), memcg->memsw.failcnt); + pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n", + K((u64)page_counter_read(&memcg->kmem)), + K((u64)memcg->kmem.max), memcg->kmem.failcnt); } +#endif + + pr_info("Memory cgroup stats for "); + pr_cont_cgroup_path(memcg->css.cgroup); + pr_cont(":"); + seq_buf_init(&s, buf, SEQ_BUF_SIZE); + memory_stat_format(memcg, &s); + seq_buf_do_printk(&s, KERN_INFO); } /* @@ -1362,441 +1604,109 @@ void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) */ unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) { - unsigned long max; + unsigned long max = READ_ONCE(memcg->memory.max); - max = memcg->memory.max; - if (mem_cgroup_swappiness(memcg)) { - unsigned long memsw_max; - unsigned long swap_max; + if (do_memsw_account()) { + if (mem_cgroup_swappiness(memcg)) { + /* Calculate swap excess capacity from memsw limit */ + unsigned long swap = READ_ONCE(memcg->memsw.max) - max; - memsw_max = memcg->memsw.max; - swap_max = memcg->swap.max; - swap_max = min(swap_max, (unsigned long)total_swap_pages); - max = min(max + swap_max, memsw_max); + max += min(swap, (unsigned long)total_swap_pages); + } + } else { + if (mem_cgroup_swappiness(memcg)) + max += min(READ_ONCE(memcg->swap.max), + (unsigned long)total_swap_pages); } return max; } -static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, - int order) -{ - struct oom_control oc = { - .zonelist = NULL, - .nodemask = NULL, - .memcg = memcg, - .gfp_mask = gfp_mask, - .order = order, - }; - bool ret; - - mutex_lock(&oom_lock); - ret = out_of_memory(&oc); - mutex_unlock(&oom_lock); - return ret; -} - -#if MAX_NUMNODES > 1 - -/** - * test_mem_cgroup_node_reclaimable - * @memcg: the target memcg - * @nid: the node ID to be checked. - * @noswap : specify true here if the user wants flle only information. - * - * This function returns whether the specified memcg contains any - * reclaimable pages on a node. Returns true if there are any reclaimable - * pages in the node. - */ -static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg, - int nid, bool noswap) -{ - if (mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL_FILE)) - return true; - if (noswap || !total_swap_pages) - return false; - if (mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL_ANON)) - return true; - return false; - -} - -/* - * Always updating the nodemask is not very good - even if we have an empty - * list or the wrong list here, we can start from some node and traverse all - * nodes based on the zonelist. So update the list loosely once per 10 secs. - * - */ -static void mem_cgroup_may_update_nodemask(struct mem_cgroup *memcg) +unsigned long mem_cgroup_size(struct mem_cgroup *memcg) { - int nid; - /* - * numainfo_events > 0 means there was at least NUMAINFO_EVENTS_TARGET - * pagein/pageout changes since the last update. - */ - if (!atomic_read(&memcg->numainfo_events)) - return; - if (atomic_inc_return(&memcg->numainfo_updating) > 1) - return; - - /* make a nodemask where this memcg uses memory from */ - memcg->scan_nodes = node_states[N_MEMORY]; - - for_each_node_mask(nid, node_states[N_MEMORY]) { - - if (!test_mem_cgroup_node_reclaimable(memcg, nid, false)) - node_clear(nid, memcg->scan_nodes); - } - - atomic_set(&memcg->numainfo_events, 0); - atomic_set(&memcg->numainfo_updating, 0); + return page_counter_read(&memcg->memory); } -/* - * Selecting a node where we start reclaim from. Because what we need is just - * reducing usage counter, start from anywhere is O,K. Considering - * memory reclaim from current node, there are pros. and cons. - * - * Freeing memory from current node means freeing memory from a node which - * we'll use or we've used. So, it may make LRU bad. And if several threads - * hit limits, it will see a contention on a node. But freeing from remote - * node means more costs for memory reclaim because of memory latency. - * - * Now, we use round-robin. Better algorithm is welcomed. - */ -int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) +void __memcg_memory_event(struct mem_cgroup *memcg, + enum memcg_memory_event event, bool allow_spinning) { - int node; - - mem_cgroup_may_update_nodemask(memcg); - node = memcg->last_scanned_node; + bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX || + event == MEMCG_SWAP_FAIL; - node = next_node_in(node, memcg->scan_nodes); - /* - * mem_cgroup_may_update_nodemask might have seen no reclaimmable pages - * last time it really checked all the LRUs due to rate limiting. - * Fallback to the current node in that case for simplicity. - */ - if (unlikely(node == MAX_NUMNODES)) - node = numa_node_id(); - - memcg->last_scanned_node = node; - return node; -} -#else -int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) -{ - return 0; -} -#endif + /* For now only MEMCG_MAX can happen with !allow_spinning context. */ + VM_WARN_ON_ONCE(!allow_spinning && event != MEMCG_MAX); -static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, - pg_data_t *pgdat, - gfp_t gfp_mask, - unsigned long *total_scanned) -{ - struct mem_cgroup *victim = NULL; - int total = 0; - int loop = 0; - unsigned long excess; - unsigned long nr_scanned; - struct mem_cgroup_reclaim_cookie reclaim = { - .pgdat = pgdat, - .priority = 0, - }; + atomic_long_inc(&memcg->memory_events_local[event]); + if (!swap_event && allow_spinning) + cgroup_file_notify(&memcg->events_local_file); - excess = soft_limit_excess(root_memcg); - - while (1) { - victim = mem_cgroup_iter(root_memcg, victim, &reclaim); - if (!victim) { - loop++; - if (loop >= 2) { - /* - * If we have not been able to reclaim - * anything, it might because there are - * no reclaimable pages under this hierarchy - */ - if (!total) - break; - /* - * We want to do more targeted reclaim. - * excess >> 2 is not to excessive so as to - * reclaim too much, nor too less that we keep - * coming back to reclaim from this cgroup - */ - if (total >= (excess >> 2) || - (loop > MEM_CGROUP_MAX_RECLAIM_LOOPS)) - break; - } - continue; + do { + atomic_long_inc(&memcg->memory_events[event]); + if (allow_spinning) { + if (swap_event) + cgroup_file_notify(&memcg->swap_events_file); + else + cgroup_file_notify(&memcg->events_file); } - total += mem_cgroup_shrink_node(victim, gfp_mask, false, - pgdat, &nr_scanned); - *total_scanned += nr_scanned; - if (!soft_limit_excess(root_memcg)) - break; - } - mem_cgroup_iter_break(root_memcg, victim); - return total; -} - -#ifdef CONFIG_LOCKDEP -static struct lockdep_map memcg_oom_lock_dep_map = { - .name = "memcg_oom_lock", -}; -#endif - -static DEFINE_SPINLOCK(memcg_oom_lock); - -/* - * Check OOM-Killer is already running under our hierarchy. - * If someone is running, return false. - */ -static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg) -{ - struct mem_cgroup *iter, *failed = NULL; - - spin_lock(&memcg_oom_lock); - for_each_mem_cgroup_tree(iter, memcg) { - if (iter->oom_lock) { - /* - * this subtree of our hierarchy is already locked - * so we cannot give a lock. - */ - failed = iter; - mem_cgroup_iter_break(memcg, iter); + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) break; - } else - iter->oom_lock = true; - } - - if (failed) { - /* - * OK, we failed to lock the whole subtree so we have - * to clean up what we set up to the failing subtree - */ - for_each_mem_cgroup_tree(iter, memcg) { - if (iter == failed) { - mem_cgroup_iter_break(memcg, iter); - break; - } - iter->oom_lock = false; - } - } else - mutex_acquire(&memcg_oom_lock_dep_map, 0, 1, _RET_IP_); - - spin_unlock(&memcg_oom_lock); - - return !failed; -} - -static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg) -{ - struct mem_cgroup *iter; - - spin_lock(&memcg_oom_lock); - mutex_release(&memcg_oom_lock_dep_map, 1, _RET_IP_); - for_each_mem_cgroup_tree(iter, memcg) - iter->oom_lock = false; - spin_unlock(&memcg_oom_lock); -} - -static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg) -{ - struct mem_cgroup *iter; - - spin_lock(&memcg_oom_lock); - for_each_mem_cgroup_tree(iter, memcg) - iter->under_oom++; - spin_unlock(&memcg_oom_lock); -} - -static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg) -{ - struct mem_cgroup *iter; - - /* - * When a new child is created while the hierarchy is under oom, - * mem_cgroup_oom_lock() may not be called. Watch for underflow. - */ - spin_lock(&memcg_oom_lock); - for_each_mem_cgroup_tree(iter, memcg) - if (iter->under_oom > 0) - iter->under_oom--; - spin_unlock(&memcg_oom_lock); -} - -static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq); - -struct oom_wait_info { - struct mem_cgroup *memcg; - wait_queue_entry_t wait; -}; - -static int memcg_oom_wake_function(wait_queue_entry_t *wait, - unsigned mode, int sync, void *arg) -{ - struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg; - struct mem_cgroup *oom_wait_memcg; - struct oom_wait_info *oom_wait_info; - - oom_wait_info = container_of(wait, struct oom_wait_info, wait); - oom_wait_memcg = oom_wait_info->memcg; - - if (!mem_cgroup_is_descendant(wake_memcg, oom_wait_memcg) && - !mem_cgroup_is_descendant(oom_wait_memcg, wake_memcg)) - return 0; - return autoremove_wake_function(wait, mode, sync, arg); -} - -static void memcg_oom_recover(struct mem_cgroup *memcg) -{ - /* - * For the following lockless ->under_oom test, the only required - * guarantee is that it must see the state asserted by an OOM when - * this function is called as a result of userland actions - * triggered by the notification of the OOM. This is trivially - * achieved by invoking mem_cgroup_mark_under_oom() before - * triggering notification. - */ - if (memcg && memcg->under_oom) - __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg); + if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) + break; + } while ((memcg = parent_mem_cgroup(memcg)) && + !mem_cgroup_is_root(memcg)); } +EXPORT_SYMBOL_GPL(__memcg_memory_event); -enum oom_status { - OOM_SUCCESS, - OOM_FAILED, - OOM_ASYNC, - OOM_SKIPPED -}; - -static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order) +static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, + int order) { - enum oom_status ret; - bool locked; + struct oom_control oc = { + .zonelist = NULL, + .nodemask = NULL, + .memcg = memcg, + .gfp_mask = gfp_mask, + .order = order, + }; + bool ret = true; - if (order > PAGE_ALLOC_COSTLY_ORDER) - return OOM_SKIPPED; + if (mutex_lock_killable(&oom_lock)) + return true; - memcg_memory_event(memcg, MEMCG_OOM); + if (mem_cgroup_margin(memcg) >= (1 << order)) + goto unlock; /* - * We are in the middle of the charge context here, so we - * don't want to block when potentially sitting on a callstack - * that holds all kinds of filesystem and mm locks. - * - * cgroup1 allows disabling the OOM killer and waiting for outside - * handling until the charge can succeed; remember the context and put - * the task to sleep at the end of the page fault when all locks are - * released. - * - * On the other hand, in-kernel OOM killer allows for an async victim - * memory reclaim (oom_reaper) and that means that we are not solely - * relying on the oom victim to make a forward progress and we can - * invoke the oom killer here. - * - * Please note that mem_cgroup_out_of_memory might fail to find a - * victim and then we have to bail out from the charge path. + * A few threads which were not waiting at mutex_lock_killable() can + * fail to bail out. Therefore, check again after holding oom_lock. */ - if (memcg->oom_kill_disable) { - if (!current->in_user_fault) - return OOM_SKIPPED; - css_get(&memcg->css); - current->memcg_in_oom = memcg; - current->memcg_oom_gfp_mask = mask; - current->memcg_oom_order = order; - - return OOM_ASYNC; - } - - mem_cgroup_mark_under_oom(memcg); - - locked = mem_cgroup_oom_trylock(memcg); - - if (locked) - mem_cgroup_oom_notify(memcg); - - mem_cgroup_unmark_under_oom(memcg); - if (mem_cgroup_out_of_memory(memcg, mask, order)) - ret = OOM_SUCCESS; - else - ret = OOM_FAILED; - - if (locked) - mem_cgroup_oom_unlock(memcg); + ret = out_of_memory(&oc); +unlock: + mutex_unlock(&oom_lock); return ret; } -/** - * mem_cgroup_oom_synchronize - complete memcg OOM handling - * @handle: actually kill/wait or just clean up the OOM state - * - * This has to be called at the end of a page fault if the memcg OOM - * handler was enabled. - * - * Memcg supports userspace OOM handling where failed allocations must - * sleep on a waitqueue until the userspace task resolves the - * situation. Sleeping directly in the charge context with all kinds - * of locks held is not a good idea, instead we remember an OOM state - * in the task and mem_cgroup_oom_synchronize() has to be called at - * the end of the page fault to complete the OOM handling. - * - * Returns %true if an ongoing memcg OOM situation was detected and - * completed, %false otherwise. +/* + * Returns true if successfully killed one or more processes. Though in some + * corner cases it can return true even without killing any process. */ -bool mem_cgroup_oom_synchronize(bool handle) +static bool mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order) { - struct mem_cgroup *memcg = current->memcg_in_oom; - struct oom_wait_info owait; - bool locked; + bool locked, ret; - /* OOM is global, do not handle */ - if (!memcg) + if (order > PAGE_ALLOC_COSTLY_ORDER) return false; - if (!handle) - goto cleanup; - - owait.memcg = memcg; - owait.wait.flags = 0; - owait.wait.func = memcg_oom_wake_function; - owait.wait.private = current; - INIT_LIST_HEAD(&owait.wait.entry); - - prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE); - mem_cgroup_mark_under_oom(memcg); + memcg_memory_event(memcg, MEMCG_OOM); - locked = mem_cgroup_oom_trylock(memcg); + if (!memcg1_oom_prepare(memcg, &locked)) + return false; - if (locked) - mem_cgroup_oom_notify(memcg); + ret = mem_cgroup_out_of_memory(memcg, mask, order); - if (locked && !memcg->oom_kill_disable) { - mem_cgroup_unmark_under_oom(memcg); - finish_wait(&memcg_oom_waitq, &owait.wait); - mem_cgroup_out_of_memory(memcg, current->memcg_oom_gfp_mask, - current->memcg_oom_order); - } else { - schedule(); - mem_cgroup_unmark_under_oom(memcg); - finish_wait(&memcg_oom_waitq, &owait.wait); - } + memcg1_oom_finish(memcg, locked); - if (locked) { - mem_cgroup_oom_unlock(memcg); - /* - * There is no guarantee that an OOM-lock contender - * sees the wakeups triggered by the OOM kill - * uncharges. Wake any sleepers explicitely. - */ - memcg_oom_recover(memcg); - } -cleanup: - current->memcg_in_oom = NULL; - css_put(&memcg->css); - return true; + return ret; } /** @@ -1824,7 +1734,15 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, rcu_read_lock(); memcg = mem_cgroup_from_task(victim); - if (memcg == root_mem_cgroup) + if (mem_cgroup_is_root(memcg)) + goto out; + + /* + * If the victim task has been asynchronously moved to a different + * memory cgroup, we might end up killing tasks outside oom_domain. + * In this case it's better to ignore memory.group.oom. + */ + if (unlikely(!mem_cgroup_is_descendant(memcg, oom_domain))) goto out; /* @@ -1833,7 +1751,7 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, * highest-level memory cgroup with oom.group set. */ for (; memcg; memcg = parent_mem_cgroup(memcg)) { - if (memcg->oom_group) + if (READ_ONCE(memcg->oom_group)) oom_group = memcg; if (memcg == oom_domain) @@ -1855,200 +1773,241 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) pr_cont(" are going to be killed due to memory.oom.group set\n"); } -/** - * lock_page_memcg - lock a page->mem_cgroup binding - * @page: the page - * - * This function protects unlocked LRU pages from being moved to - * another cgroup. - * - * It ensures lifetime of the returned memcg. Caller is responsible - * for the lifetime of the page; __unlock_page_memcg() is available - * when @page might get freed inside the locked section. - */ -struct mem_cgroup *lock_page_memcg(struct page *page) -{ - struct mem_cgroup *memcg; - unsigned long flags; - - /* - * The RCU lock is held throughout the transaction. The fast - * path can get away without acquiring the memcg->move_lock - * because page moving starts with an RCU grace period. - * - * The RCU lock also protects the memcg from being freed when - * the page state that is going to change is the only thing - * preventing the page itself from being freed. E.g. writeback - * doesn't hold a page reference and relies on PG_writeback to - * keep off truncation, migration and so forth. - */ - rcu_read_lock(); - - if (mem_cgroup_disabled()) - return NULL; -again: - memcg = page->mem_cgroup; - if (unlikely(!memcg)) - return NULL; - - if (atomic_read(&memcg->moving_account) <= 0) - return memcg; - - spin_lock_irqsave(&memcg->move_lock, flags); - if (memcg != page->mem_cgroup) { - spin_unlock_irqrestore(&memcg->move_lock, flags); - goto again; - } - - /* - * When charge migration first begins, we can have locked and - * unlocked page stat updates happening concurrently. Track - * the task who has the lock for unlock_page_memcg(). - */ - memcg->move_lock_task = current; - memcg->move_lock_flags = flags; - - return memcg; -} -EXPORT_SYMBOL(lock_page_memcg); - -/** - * __unlock_page_memcg - unlock and unpin a memcg - * @memcg: the memcg - * - * Unlock and unpin a memcg returned by lock_page_memcg(). +/* + * The value of NR_MEMCG_STOCK is selected to keep the cached memcgs and their + * nr_pages in a single cacheline. This may change in future. */ -void __unlock_page_memcg(struct mem_cgroup *memcg) -{ - if (memcg && memcg->move_lock_task == current) { - unsigned long flags = memcg->move_lock_flags; - - memcg->move_lock_task = NULL; - memcg->move_lock_flags = 0; +#define NR_MEMCG_STOCK 7 +#define FLUSHING_CACHED_CHARGE 0 +struct memcg_stock_pcp { + local_trylock_t lock; + uint8_t nr_pages[NR_MEMCG_STOCK]; + struct mem_cgroup *cached[NR_MEMCG_STOCK]; - spin_unlock_irqrestore(&memcg->move_lock, flags); - } + struct work_struct work; + unsigned long flags; +}; - rcu_read_unlock(); -} +static DEFINE_PER_CPU_ALIGNED(struct memcg_stock_pcp, memcg_stock) = { + .lock = INIT_LOCAL_TRYLOCK(lock), +}; -/** - * unlock_page_memcg - unlock a page->mem_cgroup binding - * @page: the page - */ -void unlock_page_memcg(struct page *page) -{ - __unlock_page_memcg(page->mem_cgroup); -} -EXPORT_SYMBOL(unlock_page_memcg); +struct obj_stock_pcp { + local_trylock_t lock; + unsigned int nr_bytes; + struct obj_cgroup *cached_objcg; + struct pglist_data *cached_pgdat; + int nr_slab_reclaimable_b; + int nr_slab_unreclaimable_b; -struct memcg_stock_pcp { - struct mem_cgroup *cached; /* this never be root cgroup */ - unsigned int nr_pages; struct work_struct work; unsigned long flags; -#define FLUSHING_CACHED_CHARGE 0 }; -static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock); + +static DEFINE_PER_CPU_ALIGNED(struct obj_stock_pcp, obj_stock) = { + .lock = INIT_LOCAL_TRYLOCK(lock), +}; + static DEFINE_MUTEX(percpu_charge_mutex); +static void drain_obj_stock(struct obj_stock_pcp *stock); +static bool obj_stock_flush_required(struct obj_stock_pcp *stock, + struct mem_cgroup *root_memcg); + /** * consume_stock: Try to consume stocked charge on this cpu. * @memcg: memcg to consume from. * @nr_pages: how many pages to charge. * - * The charges will only happen if @memcg matches the current cpu's memcg - * stock, and at least @nr_pages are available in that stock. Failure to - * service an allocation will refill the stock. + * Consume the cached charge if enough nr_pages are present otherwise return + * failure. Also return failure for charge request larger than + * MEMCG_CHARGE_BATCH or if the local lock is already taken. * * returns true if successful, false otherwise. */ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages) { struct memcg_stock_pcp *stock; - unsigned long flags; + uint8_t stock_pages; bool ret = false; + int i; - if (nr_pages > MEMCG_CHARGE_BATCH) + if (nr_pages > MEMCG_CHARGE_BATCH || + !local_trylock(&memcg_stock.lock)) return ret; - local_irq_save(flags); - stock = this_cpu_ptr(&memcg_stock); - if (memcg == stock->cached && stock->nr_pages >= nr_pages) { - stock->nr_pages -= nr_pages; - ret = true; + + for (i = 0; i < NR_MEMCG_STOCK; ++i) { + if (memcg != READ_ONCE(stock->cached[i])) + continue; + + stock_pages = READ_ONCE(stock->nr_pages[i]); + if (stock_pages >= nr_pages) { + WRITE_ONCE(stock->nr_pages[i], stock_pages - nr_pages); + ret = true; + } + break; } - local_irq_restore(flags); + local_unlock(&memcg_stock.lock); return ret; } +static void memcg_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages) +{ + page_counter_uncharge(&memcg->memory, nr_pages); + if (do_memsw_account()) + page_counter_uncharge(&memcg->memsw, nr_pages); +} + /* * Returns stocks cached in percpu and reset cached information. */ -static void drain_stock(struct memcg_stock_pcp *stock) +static void drain_stock(struct memcg_stock_pcp *stock, int i) { - struct mem_cgroup *old = stock->cached; + struct mem_cgroup *old = READ_ONCE(stock->cached[i]); + uint8_t stock_pages; - if (stock->nr_pages) { - page_counter_uncharge(&old->memory, stock->nr_pages); - if (do_memsw_account()) - page_counter_uncharge(&old->memsw, stock->nr_pages); - css_put_many(&old->css, stock->nr_pages); - stock->nr_pages = 0; + if (!old) + return; + + stock_pages = READ_ONCE(stock->nr_pages[i]); + if (stock_pages) { + memcg_uncharge(old, stock_pages); + WRITE_ONCE(stock->nr_pages[i], 0); } - stock->cached = NULL; + + css_put(&old->css); + WRITE_ONCE(stock->cached[i], NULL); } -static void drain_local_stock(struct work_struct *dummy) +static void drain_stock_fully(struct memcg_stock_pcp *stock) +{ + int i; + + for (i = 0; i < NR_MEMCG_STOCK; ++i) + drain_stock(stock, i); +} + +static void drain_local_memcg_stock(struct work_struct *dummy) { struct memcg_stock_pcp *stock; - unsigned long flags; - /* - * The only protection from memory hotplug vs. drain_stock races is - * that we always operate on local CPU stock here with IRQ disabled - */ - local_irq_save(flags); + if (WARN_ONCE(!in_task(), "drain in non-task context")) + return; + + local_lock(&memcg_stock.lock); stock = this_cpu_ptr(&memcg_stock); - drain_stock(stock); + drain_stock_fully(stock); clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); - local_irq_restore(flags); + local_unlock(&memcg_stock.lock); +} + +static void drain_local_obj_stock(struct work_struct *dummy) +{ + struct obj_stock_pcp *stock; + + if (WARN_ONCE(!in_task(), "drain in non-task context")) + return; + + local_lock(&obj_stock.lock); + + stock = this_cpu_ptr(&obj_stock); + drain_obj_stock(stock); + clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); + + local_unlock(&obj_stock.lock); } -/* - * Cache charges(val) to local per_cpu area. - * This will be consumed by consume_stock() function, later. - */ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages) { struct memcg_stock_pcp *stock; - unsigned long flags; + struct mem_cgroup *cached; + uint8_t stock_pages; + bool success = false; + int empty_slot = -1; + int i; - local_irq_save(flags); + /* + * For now limit MEMCG_CHARGE_BATCH to 127 and less. In future if we + * decide to increase it more than 127 then we will need more careful + * handling of nr_pages[] in struct memcg_stock_pcp. + */ + BUILD_BUG_ON(MEMCG_CHARGE_BATCH > S8_MAX); + + VM_WARN_ON_ONCE(mem_cgroup_is_root(memcg)); + + if (nr_pages > MEMCG_CHARGE_BATCH || + !local_trylock(&memcg_stock.lock)) { + /* + * In case of larger than batch refill or unlikely failure to + * lock the percpu memcg_stock.lock, uncharge memcg directly. + */ + memcg_uncharge(memcg, nr_pages); + return; + } stock = this_cpu_ptr(&memcg_stock); - if (stock->cached != memcg) { /* reset if necessary */ - drain_stock(stock); - stock->cached = memcg; + for (i = 0; i < NR_MEMCG_STOCK; ++i) { + cached = READ_ONCE(stock->cached[i]); + if (!cached && empty_slot == -1) + empty_slot = i; + if (memcg == READ_ONCE(stock->cached[i])) { + stock_pages = READ_ONCE(stock->nr_pages[i]) + nr_pages; + WRITE_ONCE(stock->nr_pages[i], stock_pages); + if (stock_pages > MEMCG_CHARGE_BATCH) + drain_stock(stock, i); + success = true; + break; + } } - stock->nr_pages += nr_pages; - if (stock->nr_pages > MEMCG_CHARGE_BATCH) - drain_stock(stock); + if (!success) { + i = empty_slot; + if (i == -1) { + i = get_random_u32_below(NR_MEMCG_STOCK); + drain_stock(stock, i); + } + css_get(&memcg->css); + WRITE_ONCE(stock->cached[i], memcg); + WRITE_ONCE(stock->nr_pages[i], nr_pages); + } - local_irq_restore(flags); + local_unlock(&memcg_stock.lock); +} + +static bool is_memcg_drain_needed(struct memcg_stock_pcp *stock, + struct mem_cgroup *root_memcg) +{ + struct mem_cgroup *memcg; + bool flush = false; + int i; + + rcu_read_lock(); + for (i = 0; i < NR_MEMCG_STOCK; ++i) { + memcg = READ_ONCE(stock->cached[i]); + if (!memcg) + continue; + + if (READ_ONCE(stock->nr_pages[i]) && + mem_cgroup_is_descendant(memcg, root_memcg)) { + flush = true; + break; + } + } + rcu_read_unlock(); + return flush; } /* * Drains all per-CPU charge caches for given root_memcg resp. subtree * of the hierarchy under it. */ -static void drain_all_stock(struct mem_cgroup *root_memcg) +void drain_all_stock(struct mem_cgroup *root_memcg) { int cpu, curcpu; @@ -2061,131 +2020,335 @@ static void drain_all_stock(struct mem_cgroup *root_memcg) * as well as workers from this path always operate on the local * per-cpu data. CPU up doesn't touch memcg_stock at all. */ - curcpu = get_cpu(); + migrate_disable(); + curcpu = smp_processor_id(); for_each_online_cpu(cpu) { - struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); - struct mem_cgroup *memcg; + struct memcg_stock_pcp *memcg_st = &per_cpu(memcg_stock, cpu); + struct obj_stock_pcp *obj_st = &per_cpu(obj_stock, cpu); - memcg = stock->cached; - if (!memcg || !stock->nr_pages || !css_tryget(&memcg->css)) - continue; - if (!mem_cgroup_is_descendant(memcg, root_memcg)) { - css_put(&memcg->css); - continue; + if (!test_bit(FLUSHING_CACHED_CHARGE, &memcg_st->flags) && + is_memcg_drain_needed(memcg_st, root_memcg) && + !test_and_set_bit(FLUSHING_CACHED_CHARGE, + &memcg_st->flags)) { + if (cpu == curcpu) + drain_local_memcg_stock(&memcg_st->work); + else if (!cpu_is_isolated(cpu)) + schedule_work_on(cpu, &memcg_st->work); } - if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) { + + if (!test_bit(FLUSHING_CACHED_CHARGE, &obj_st->flags) && + obj_stock_flush_required(obj_st, root_memcg) && + !test_and_set_bit(FLUSHING_CACHED_CHARGE, + &obj_st->flags)) { if (cpu == curcpu) - drain_local_stock(&stock->work); - else - schedule_work_on(cpu, &stock->work); + drain_local_obj_stock(&obj_st->work); + else if (!cpu_is_isolated(cpu)) + schedule_work_on(cpu, &obj_st->work); } - css_put(&memcg->css); } - put_cpu(); + migrate_enable(); mutex_unlock(&percpu_charge_mutex); } static int memcg_hotplug_cpu_dead(unsigned int cpu) { - struct memcg_stock_pcp *stock; + /* no need for the local lock */ + drain_obj_stock(&per_cpu(obj_stock, cpu)); + drain_stock_fully(&per_cpu(memcg_stock, cpu)); + + return 0; +} + +static unsigned long reclaim_high(struct mem_cgroup *memcg, + unsigned int nr_pages, + gfp_t gfp_mask) +{ + unsigned long nr_reclaimed = 0; + + do { + unsigned long pflags; + + if (page_counter_read(&memcg->memory) <= + READ_ONCE(memcg->memory.high)) + continue; + + memcg_memory_event(memcg, MEMCG_HIGH); + + psi_memstall_enter(&pflags); + nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages, + gfp_mask, + MEMCG_RECLAIM_MAY_SWAP, + NULL); + psi_memstall_leave(&pflags); + } while ((memcg = parent_mem_cgroup(memcg)) && + !mem_cgroup_is_root(memcg)); + + return nr_reclaimed; +} + +static void high_work_func(struct work_struct *work) +{ struct mem_cgroup *memcg; - stock = &per_cpu(memcg_stock, cpu); - drain_stock(stock); + memcg = container_of(work, struct mem_cgroup, high_work); + reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL); +} - for_each_mem_cgroup(memcg) { - int i; +/* + * Clamp the maximum sleep time per allocation batch to 2 seconds. This is + * enough to still cause a significant slowdown in most cases, while still + * allowing diagnostics and tracing to proceed without becoming stuck. + */ +#define MEMCG_MAX_HIGH_DELAY_JIFFIES (2UL*HZ) - for (i = 0; i < MEMCG_NR_STAT; i++) { - int nid; - long x; +/* + * When calculating the delay, we use these either side of the exponentiation to + * maintain precision and scale to a reasonable number of jiffies (see the table + * below. + * + * - MEMCG_DELAY_PRECISION_SHIFT: Extra precision bits while translating the + * overage ratio to a delay. + * - MEMCG_DELAY_SCALING_SHIFT: The number of bits to scale down the + * proposed penalty in order to reduce to a reasonable number of jiffies, and + * to produce a reasonable delay curve. + * + * MEMCG_DELAY_SCALING_SHIFT just happens to be a number that produces a + * reasonable delay curve compared to precision-adjusted overage, not + * penalising heavily at first, but still making sure that growth beyond the + * limit penalises misbehaviour cgroups by slowing them down exponentially. For + * example, with a high of 100 megabytes: + * + * +-------+------------------------+ + * | usage | time to allocate in ms | + * +-------+------------------------+ + * | 100M | 0 | + * | 101M | 6 | + * | 102M | 25 | + * | 103M | 57 | + * | 104M | 102 | + * | 105M | 159 | + * | 106M | 230 | + * | 107M | 313 | + * | 108M | 409 | + * | 109M | 518 | + * | 110M | 639 | + * | 111M | 774 | + * | 112M | 921 | + * | 113M | 1081 | + * | 114M | 1254 | + * | 115M | 1439 | + * | 116M | 1638 | + * | 117M | 1849 | + * | 118M | 2000 | + * | 119M | 2000 | + * | 120M | 2000 | + * +-------+------------------------+ + */ + #define MEMCG_DELAY_PRECISION_SHIFT 20 + #define MEMCG_DELAY_SCALING_SHIFT 14 - x = this_cpu_xchg(memcg->stat_cpu->count[i], 0); - if (x) - atomic_long_add(x, &memcg->stat[i]); +static u64 calculate_overage(unsigned long usage, unsigned long high) +{ + u64 overage; - if (i >= NR_VM_NODE_STAT_ITEMS) - continue; + if (usage <= high) + return 0; - for_each_node(nid) { - struct mem_cgroup_per_node *pn; + /* + * Prevent division by 0 in overage calculation by acting as if + * it was a threshold of 1 page + */ + high = max(high, 1UL); - pn = mem_cgroup_nodeinfo(memcg, nid); - x = this_cpu_xchg(pn->lruvec_stat_cpu->count[i], 0); - if (x) - atomic_long_add(x, &pn->lruvec_stat[i]); - } - } + overage = usage - high; + overage <<= MEMCG_DELAY_PRECISION_SHIFT; + return div64_u64(overage, high); +} - for (i = 0; i < NR_VM_EVENT_ITEMS; i++) { - long x; +static u64 mem_find_max_overage(struct mem_cgroup *memcg) +{ + u64 overage, max_overage = 0; - x = this_cpu_xchg(memcg->stat_cpu->events[i], 0); - if (x) - atomic_long_add(x, &memcg->events[i]); - } - } + do { + overage = calculate_overage(page_counter_read(&memcg->memory), + READ_ONCE(memcg->memory.high)); + max_overage = max(overage, max_overage); + } while ((memcg = parent_mem_cgroup(memcg)) && + !mem_cgroup_is_root(memcg)); - return 0; + return max_overage; } -static void reclaim_high(struct mem_cgroup *memcg, - unsigned int nr_pages, - gfp_t gfp_mask) +static u64 swap_find_max_overage(struct mem_cgroup *memcg) { + u64 overage, max_overage = 0; + do { - if (page_counter_read(&memcg->memory) <= memcg->high) - continue; - memcg_memory_event(memcg, MEMCG_HIGH); - try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true); - } while ((memcg = parent_mem_cgroup(memcg))); + overage = calculate_overage(page_counter_read(&memcg->swap), + READ_ONCE(memcg->swap.high)); + if (overage) + memcg_memory_event(memcg, MEMCG_SWAP_HIGH); + max_overage = max(overage, max_overage); + } while ((memcg = parent_mem_cgroup(memcg)) && + !mem_cgroup_is_root(memcg)); + + return max_overage; } -static void high_work_func(struct work_struct *work) +/* + * Get the number of jiffies that we should penalise a mischievous cgroup which + * is exceeding its memory.high by checking both it and its ancestors. + */ +static unsigned long calculate_high_delay(struct mem_cgroup *memcg, + unsigned int nr_pages, + u64 max_overage) { - struct mem_cgroup *memcg; + unsigned long penalty_jiffies; - memcg = container_of(work, struct mem_cgroup, high_work); - reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL); + if (!max_overage) + return 0; + + /* + * We use overage compared to memory.high to calculate the number of + * jiffies to sleep (penalty_jiffies). Ideally this value should be + * fairly lenient on small overages, and increasingly harsh when the + * memcg in question makes it clear that it has no intention of stopping + * its crazy behaviour, so we exponentially increase the delay based on + * overage amount. + */ + penalty_jiffies = max_overage * max_overage * HZ; + penalty_jiffies >>= MEMCG_DELAY_PRECISION_SHIFT; + penalty_jiffies >>= MEMCG_DELAY_SCALING_SHIFT; + + /* + * Factor in the task's own contribution to the overage, such that four + * N-sized allocations are throttled approximately the same as one + * 4N-sized allocation. + * + * MEMCG_CHARGE_BATCH pages is nominal, so work out how much smaller or + * larger the current charge patch is than that. + */ + return penalty_jiffies * nr_pages / MEMCG_CHARGE_BATCH; } /* - * Scheduled by try_charge() to be executed from the userland return path - * and reclaims memory over the high limit. + * Reclaims memory over the high limit. Called directly from + * try_charge() (context permitting), as well as from the userland + * return path where reclaim is always able to block. */ -void mem_cgroup_handle_over_high(void) +void __mem_cgroup_handle_over_high(gfp_t gfp_mask) { + unsigned long penalty_jiffies; + unsigned long pflags; + unsigned long nr_reclaimed; unsigned int nr_pages = current->memcg_nr_pages_over_high; + int nr_retries = MAX_RECLAIM_RETRIES; struct mem_cgroup *memcg; - - if (likely(!nr_pages)) - return; + bool in_retry = false; memcg = get_mem_cgroup_from_mm(current->mm); - reclaim_high(memcg, nr_pages, GFP_KERNEL); - css_put(&memcg->css); current->memcg_nr_pages_over_high = 0; + +retry_reclaim: + /* + * Bail if the task is already exiting. Unlike memory.max, + * memory.high enforcement isn't as strict, and there is no + * OOM killer involved, which means the excess could already + * be much bigger (and still growing) than it could for + * memory.max; the dying task could get stuck in fruitless + * reclaim for a long time, which isn't desirable. + */ + if (task_is_dying()) + goto out; + + /* + * The allocating task should reclaim at least the batch size, but for + * subsequent retries we only want to do what's necessary to prevent oom + * or breaching resource isolation. + * + * This is distinct from memory.max or page allocator behaviour because + * memory.high is currently batched, whereas memory.max and the page + * allocator run every time an allocation is made. + */ + nr_reclaimed = reclaim_high(memcg, + in_retry ? SWAP_CLUSTER_MAX : nr_pages, + gfp_mask); + + /* + * memory.high is breached and reclaim is unable to keep up. Throttle + * allocators proactively to slow down excessive growth. + */ + penalty_jiffies = calculate_high_delay(memcg, nr_pages, + mem_find_max_overage(memcg)); + + penalty_jiffies += calculate_high_delay(memcg, nr_pages, + swap_find_max_overage(memcg)); + + /* + * Clamp the max delay per usermode return so as to still keep the + * application moving forwards and also permit diagnostics, albeit + * extremely slowly. + */ + penalty_jiffies = min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES); + + /* + * Don't sleep if the amount of jiffies this memcg owes us is so low + * that it's not even worth doing, in an attempt to be nice to those who + * go only a small amount over their memory.high value and maybe haven't + * been aggressively reclaimed enough yet. + */ + if (penalty_jiffies <= HZ / 100) + goto out; + + /* + * If reclaim is making forward progress but we're still over + * memory.high, we want to encourage that rather than doing allocator + * throttling. + */ + if (nr_reclaimed || nr_retries--) { + in_retry = true; + goto retry_reclaim; + } + + /* + * Reclaim didn't manage to push usage below the limit, slow + * this allocating task down. + * + * If we exit early, we're guaranteed to die (since + * schedule_timeout_killable sets TASK_KILLABLE). This means we don't + * need to account for any ill-begotten jiffies to pay them off later. + */ + psi_memstall_enter(&pflags); + schedule_timeout_killable(penalty_jiffies); + psi_memstall_leave(&pflags); + +out: + css_put(&memcg->css); } -static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, - unsigned int nr_pages) +static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask, + unsigned int nr_pages) { unsigned int batch = max(MEMCG_CHARGE_BATCH, nr_pages); - int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; + int nr_retries = MAX_RECLAIM_RETRIES; struct mem_cgroup *mem_over_limit; struct page_counter *counter; unsigned long nr_reclaimed; - bool may_swap = true; + bool passed_oom = false; + unsigned int reclaim_options = MEMCG_RECLAIM_MAY_SWAP; bool drained = false; - bool oomed = false; - enum oom_status oom_status; + bool raised_max_event = false; + unsigned long pflags; + bool allow_spinning = gfpflags_allow_spinning(gfp_mask); - if (mem_cgroup_is_root(memcg)) - return 0; retry: if (consume_stock(memcg, nr_pages)) return 0; + if (!allow_spinning) + /* Avoid the refill and flush of the older stock */ + batch = nr_pages; + if (!do_memsw_account() || page_counter_try_charge(&memcg->memsw, batch, &counter)) { if (page_counter_try_charge(&memcg->memory, batch, &counter)) @@ -2195,7 +2358,7 @@ retry: mem_over_limit = mem_cgroup_from_counter(counter, memory); } else { mem_over_limit = mem_cgroup_from_counter(counter, memsw); - may_swap = false; + reclaim_options &= ~MEMCG_RECLAIM_MAY_SWAP; } if (batch > nr_pages) { @@ -2204,17 +2367,6 @@ retry: } /* - * Unlike in global OOM situations, memcg is not in a physical - * memory shortage. Allow dying and OOM-killed tasks to - * bypass the last charges so that they can exit quickly and - * free their memory. - */ - if (unlikely(tsk_is_oom_victim(current) || - fatal_signal_pending(current) || - current->flags & PF_EXITING)) - goto force; - - /* * Prevent unbounded recursion when reclaim operations need to * allocate memory. This might exceed the limits temporarily, * but we prefer facilitating memory reclaim and getting back @@ -2229,10 +2381,13 @@ retry: if (!gfpflags_allow_blocking(gfp_mask)) goto nomem; - memcg_memory_event(mem_over_limit, MEMCG_MAX); + __memcg_memory_event(mem_over_limit, MEMCG_MAX, allow_spinning); + raised_max_event = true; + psi_memstall_enter(&pflags); nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, - gfp_mask, may_swap); + gfp_mask, reclaim_options, NULL); + psi_memstall_leave(&pflags); if (mem_cgroup_margin(mem_over_limit) >= nr_pages) goto retry; @@ -2256,47 +2411,46 @@ retry: */ if (nr_reclaimed && nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER)) goto retry; - /* - * At task move, charge accounts can be doubly counted. So, it's - * better to wait until the end of task_move if something is going on. - */ - if (mem_cgroup_wait_acct_move(mem_over_limit)) - goto retry; if (nr_retries--) goto retry; - if (gfp_mask & __GFP_RETRY_MAYFAIL && oomed) + if (gfp_mask & __GFP_RETRY_MAYFAIL) goto nomem; - if (gfp_mask & __GFP_NOFAIL) - goto force; - - if (fatal_signal_pending(current)) - goto force; + /* Avoid endless loop for tasks bypassed by the oom killer */ + if (passed_oom && task_is_dying()) + goto nomem; /* * keep retrying as long as the memcg oom killer is able to make * a forward progress or bypass the charge if the oom killer * couldn't make any progress. */ - oom_status = mem_cgroup_oom(mem_over_limit, gfp_mask, - get_order(nr_pages * PAGE_SIZE)); - switch (oom_status) { - case OOM_SUCCESS: - nr_retries = MEM_CGROUP_RECLAIM_RETRIES; - oomed = true; + if (mem_cgroup_oom(mem_over_limit, gfp_mask, + get_order(nr_pages * PAGE_SIZE))) { + passed_oom = true; + nr_retries = MAX_RECLAIM_RETRIES; goto retry; - case OOM_FAILED: - goto force; - default: - goto nomem; } nomem: - if (!(gfp_mask & __GFP_NOFAIL)) + /* + * Memcg doesn't have a dedicated reserve for atomic + * allocations. But like the global atomic pool, we need to + * put the burden of reclaim on regular allocation requests + * and let these go through as privileged allocations. + */ + if (!(gfp_mask & (__GFP_NOFAIL | __GFP_HIGH))) return -ENOMEM; force: /* + * If the allocation has to be enforced, don't forget to raise + * a MEMCG_MAX event. + */ + if (!raised_max_event) + __memcg_memory_event(mem_over_limit, MEMCG_MAX, allow_spinning); + + /* * The allocation either can't fail or will lead to more memory * being freed very soon. Allow memory usage go over the limit * temporarily by force charging it. @@ -2304,12 +2458,10 @@ force: page_counter_charge(&memcg->memory, nr_pages); if (do_memsw_account()) page_counter_charge(&memcg->memsw, nr_pages); - css_get_many(&memcg->css, nr_pages); return 0; done_restock: - css_get_many(&memcg->css, batch); if (batch > nr_pages) refill_stock(memcg, batch - nr_pages); @@ -2323,1531 +2475,878 @@ done_restock: * reclaim, the cost of mismatch is negligible. */ do { - if (page_counter_read(&memcg->memory) > memcg->high) { - /* Don't bother a random interrupted task */ - if (in_interrupt()) { + bool mem_high, swap_high; + + mem_high = page_counter_read(&memcg->memory) > + READ_ONCE(memcg->memory.high); + swap_high = page_counter_read(&memcg->swap) > + READ_ONCE(memcg->swap.high); + + /* Don't bother a random interrupted task */ + if (!in_task()) { + if (mem_high) { schedule_work(&memcg->high_work); break; } + continue; + } + + if (mem_high || swap_high) { + /* + * The allocating tasks in this cgroup will need to do + * reclaim or be throttled to prevent further growth + * of the memory or swap footprints. + * + * Target some best-effort fairness between the tasks, + * and distribute reclaim work and delay penalties + * based on how much each task is actually allocating. + */ current->memcg_nr_pages_over_high += batch; set_notify_resume(current); break; } } while ((memcg = parent_mem_cgroup(memcg))); + /* + * Reclaim is set up above to be called from the userland + * return path. But also attempt synchronous reclaim to avoid + * excessive overrun while the task is still inside the + * kernel. If this is successful, the return path will see it + * when it rechecks the overage and simply bail out. + */ + if (current->memcg_nr_pages_over_high > MEMCG_CHARGE_BATCH && + !(current->flags & PF_MEMALLOC) && + gfpflags_allow_blocking(gfp_mask)) + __mem_cgroup_handle_over_high(gfp_mask); return 0; } -static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) +static inline int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, + unsigned int nr_pages) { if (mem_cgroup_is_root(memcg)) - return; - - page_counter_uncharge(&memcg->memory, nr_pages); - if (do_memsw_account()) - page_counter_uncharge(&memcg->memsw, nr_pages); - - css_put_many(&memcg->css, nr_pages); -} - -static void lock_page_lru(struct page *page, int *isolated) -{ - struct zone *zone = page_zone(page); - - spin_lock_irq(zone_lru_lock(zone)); - if (PageLRU(page)) { - struct lruvec *lruvec; - - lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); - ClearPageLRU(page); - del_page_from_lru_list(page, lruvec, page_lru(page)); - *isolated = 1; - } else - *isolated = 0; -} - -static void unlock_page_lru(struct page *page, int isolated) -{ - struct zone *zone = page_zone(page); - - if (isolated) { - struct lruvec *lruvec; + return 0; - lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); - VM_BUG_ON_PAGE(PageLRU(page), page); - SetPageLRU(page); - add_page_to_lru_list(page, lruvec, page_lru(page)); - } - spin_unlock_irq(zone_lru_lock(zone)); + return try_charge_memcg(memcg, gfp_mask, nr_pages); } -static void commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare) +static void commit_charge(struct folio *folio, struct mem_cgroup *memcg) { - int isolated; - - VM_BUG_ON_PAGE(page->mem_cgroup, page); - + VM_BUG_ON_FOLIO(folio_memcg_charged(folio), folio); /* - * In some cases, SwapCache and FUSE(splice_buf->radixtree), the page - * may already be on some other mem_cgroup's LRU. Take care of it. - */ - if (lrucare) - lock_page_lru(page, &isolated); - - /* - * Nobody should be changing or seriously looking at - * page->mem_cgroup at this point: - * - * - the page is uncharged - * - * - the page is off-LRU - * - * - an anonymous fault has exclusive page access, except for - * a locked page table + * Any of the following ensures page's memcg stability: * - * - a page cache insertion, a swapin fault, or a migration - * have the page locked + * - the page lock + * - LRU isolation + * - exclusive reference */ - page->mem_cgroup = memcg; - - if (lrucare) - unlock_page_lru(page, isolated); + folio->memcg_data = (unsigned long)memcg; } -#ifdef CONFIG_MEMCG_KMEM -static int memcg_alloc_cache_id(void) +#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC +static inline void account_slab_nmi_safe(struct mem_cgroup *memcg, + struct pglist_data *pgdat, + enum node_stat_item idx, int nr) { - int id, size; - int err; - - id = ida_simple_get(&memcg_cache_ida, - 0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL); - if (id < 0) - return id; - - if (id < memcg_nr_cache_ids) - return id; - - /* - * There's no space for the new id in memcg_caches arrays, - * so we have to grow them. - */ - down_write(&memcg_cache_ids_sem); - - size = 2 * (id + 1); - if (size < MEMCG_CACHES_MIN_SIZE) - size = MEMCG_CACHES_MIN_SIZE; - else if (size > MEMCG_CACHES_MAX_SIZE) - size = MEMCG_CACHES_MAX_SIZE; - - err = memcg_update_all_caches(size); - if (!err) - err = memcg_update_all_list_lrus(size); - if (!err) - memcg_nr_cache_ids = size; + struct lruvec *lruvec; - up_write(&memcg_cache_ids_sem); + if (likely(!in_nmi())) { + lruvec = mem_cgroup_lruvec(memcg, pgdat); + mod_memcg_lruvec_state(lruvec, idx, nr); + } else { + struct mem_cgroup_per_node *pn = memcg->nodeinfo[pgdat->node_id]; - if (err) { - ida_simple_remove(&memcg_cache_ida, id); - return err; + /* preemption is disabled in_nmi(). */ + css_rstat_updated(&memcg->css, smp_processor_id()); + if (idx == NR_SLAB_RECLAIMABLE_B) + atomic_add(nr, &pn->slab_reclaimable); + else + atomic_add(nr, &pn->slab_unreclaimable); } - return id; -} - -static void memcg_free_cache_id(int id) -{ - ida_simple_remove(&memcg_cache_ida, id); } - -struct memcg_kmem_cache_create_work { - struct mem_cgroup *memcg; - struct kmem_cache *cachep; - struct work_struct work; -}; - -static void memcg_kmem_cache_create_func(struct work_struct *w) +#else +static inline void account_slab_nmi_safe(struct mem_cgroup *memcg, + struct pglist_data *pgdat, + enum node_stat_item idx, int nr) { - struct memcg_kmem_cache_create_work *cw = - container_of(w, struct memcg_kmem_cache_create_work, work); - struct mem_cgroup *memcg = cw->memcg; - struct kmem_cache *cachep = cw->cachep; - - memcg_create_kmem_cache(memcg, cachep); + struct lruvec *lruvec; - css_put(&memcg->css); - kfree(cw); + lruvec = mem_cgroup_lruvec(memcg, pgdat); + mod_memcg_lruvec_state(lruvec, idx, nr); } +#endif -/* - * Enqueue the creation of a per-memcg kmem_cache. - */ -static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static inline void mod_objcg_mlstate(struct obj_cgroup *objcg, + struct pglist_data *pgdat, + enum node_stat_item idx, int nr) { - struct memcg_kmem_cache_create_work *cw; - - cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN); - if (!cw) - return; - - css_get(&memcg->css); - - cw->memcg = memcg; - cw->cachep = cachep; - INIT_WORK(&cw->work, memcg_kmem_cache_create_func); - - queue_work(memcg_kmem_cache_wq, &cw->work); -} + struct mem_cgroup *memcg; -static inline bool memcg_kmem_bypass(void) -{ - if (in_interrupt() || !current->mm || (current->flags & PF_KTHREAD)) - return true; - return false; + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + account_slab_nmi_safe(memcg, pgdat, idx, nr); + rcu_read_unlock(); } -/** - * memcg_kmem_get_cache: select the correct per-memcg cache for allocation - * @cachep: the original global kmem cache - * - * Return the kmem_cache we're supposed to use for a slab allocation. - * We try to use the current memcg's version of the cache. - * - * If the cache does not exist yet, if we are the first user of it, we - * create it asynchronously in a workqueue and let the current allocation - * go through with the original cache. - * - * This function takes a reference to the cache it returns to assure it - * won't get destroyed while we are working with it. Once the caller is - * done with it, memcg_kmem_put_cache() must be called to release the - * reference. - */ -struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep) +static __always_inline +struct mem_cgroup *mem_cgroup_from_obj_slab(struct slab *slab, void *p) { - struct mem_cgroup *memcg; - struct kmem_cache *memcg_cachep; - int kmemcg_id; - - VM_BUG_ON(!is_root_cache(cachep)); - - if (memcg_kmem_bypass()) - return cachep; - - memcg = get_mem_cgroup_from_current(); - kmemcg_id = READ_ONCE(memcg->kmemcg_id); - if (kmemcg_id < 0) - goto out; - - memcg_cachep = cache_from_memcg_idx(cachep, kmemcg_id); - if (likely(memcg_cachep)) - return memcg_cachep; - /* - * If we are in a safe context (can wait, and not in interrupt - * context), we could be be predictable and return right away. - * This would guarantee that the allocation being performed - * already belongs in the new cache. - * - * However, there are some clashes that can arrive from locking. - * For instance, because we acquire the slab_mutex while doing - * memcg_create_kmem_cache, this means no further allocation - * could happen with the slab_mutex held. So it's better to - * defer everything. + * Slab objects are accounted individually, not per-page. + * Memcg membership data for each individual object is saved in + * slab->obj_exts. */ - memcg_schedule_kmem_cache_create(memcg, cachep); -out: - css_put(&memcg->css); - return cachep; -} - -/** - * memcg_kmem_put_cache: drop reference taken by memcg_kmem_get_cache - * @cachep: the cache returned by memcg_kmem_get_cache - */ -void memcg_kmem_put_cache(struct kmem_cache *cachep) -{ - if (!is_root_cache(cachep)) - css_put(&cachep->memcg_params.memcg->css); -} - -/** - * memcg_kmem_charge_memcg: charge a kmem page - * @page: page to charge - * @gfp: reclaim mode - * @order: allocation order - * @memcg: memory cgroup to charge - * - * Returns 0 on success, an error code on failure. - */ -int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, - struct mem_cgroup *memcg) -{ - unsigned int nr_pages = 1 << order; - struct page_counter *counter; - int ret; - - ret = try_charge(memcg, gfp, nr_pages); - if (ret) - return ret; - - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && - !page_counter_try_charge(&memcg->kmem, nr_pages, &counter)) { - cancel_charge(memcg, nr_pages); - return -ENOMEM; - } - - page->mem_cgroup = memcg; - - return 0; -} - -/** - * memcg_kmem_charge: charge a kmem page to the current memory cgroup - * @page: page to charge - * @gfp: reclaim mode - * @order: allocation order - * - * Returns 0 on success, an error code on failure. - */ -int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) -{ - struct mem_cgroup *memcg; - int ret = 0; - - if (mem_cgroup_disabled() || memcg_kmem_bypass()) - return 0; - - memcg = get_mem_cgroup_from_current(); - if (!mem_cgroup_is_root(memcg)) { - ret = memcg_kmem_charge_memcg(page, gfp, order, memcg); - if (!ret) - __SetPageKmemcg(page); - } - css_put(&memcg->css); - return ret; -} -/** - * memcg_kmem_uncharge: uncharge a kmem page - * @page: page to uncharge - * @order: allocation order - */ -void memcg_kmem_uncharge(struct page *page, int order) -{ - struct mem_cgroup *memcg = page->mem_cgroup; - unsigned int nr_pages = 1 << order; + struct slabobj_ext *obj_exts; + unsigned int off; - if (!memcg) - return; - - VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page); - - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) - page_counter_uncharge(&memcg->kmem, nr_pages); - - page_counter_uncharge(&memcg->memory, nr_pages); - if (do_memsw_account()) - page_counter_uncharge(&memcg->memsw, nr_pages); - - page->mem_cgroup = NULL; + obj_exts = slab_obj_exts(slab); + if (!obj_exts) + return NULL; - /* slab pages do not have PageKmemcg flag set */ - if (PageKmemcg(page)) - __ClearPageKmemcg(page); + off = obj_to_index(slab->slab_cache, slab, p); + if (obj_exts[off].objcg) + return obj_cgroup_memcg(obj_exts[off].objcg); - css_put_many(&memcg->css, nr_pages); + return NULL; } -#endif /* CONFIG_MEMCG_KMEM */ - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* - * Because tail pages are not marked as "used", set it. We're under - * zone_lru_lock and migration entries setup in all page mappings. + * Returns a pointer to the memory cgroup to which the kernel object is charged. + * It is not suitable for objects allocated using vmalloc(). + * + * A passed kernel object must be a slab object or a generic kernel page. + * + * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(), + * cgroup_mutex, etc. */ -void mem_cgroup_split_huge_fixup(struct page *head) +struct mem_cgroup *mem_cgroup_from_slab_obj(void *p) { - int i; + struct slab *slab; if (mem_cgroup_disabled()) - return; - - for (i = 1; i < HPAGE_PMD_NR; i++) - head[i].mem_cgroup = head->mem_cgroup; + return NULL; - __mod_memcg_state(head->mem_cgroup, MEMCG_RSS_HUGE, -HPAGE_PMD_NR); + slab = virt_to_slab(p); + if (slab) + return mem_cgroup_from_obj_slab(slab, p); + return folio_memcg_check(virt_to_folio(p)); } -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -#ifdef CONFIG_MEMCG_SWAP -/** - * mem_cgroup_move_swap_account - move swap charge and swap_cgroup's record. - * @entry: swap entry to be moved - * @from: mem_cgroup which the entry is moved from - * @to: mem_cgroup which the entry is moved to - * - * It succeeds only when the swap_cgroup's record for this entry is the same - * as the mem_cgroup's id of @from. - * - * Returns 0 on success, -EINVAL on failure. - * - * The caller must have charged to @to, IOW, called page_counter_charge() about - * both res and memsw, and called css_get(). - */ -static int mem_cgroup_move_swap_account(swp_entry_t entry, - struct mem_cgroup *from, struct mem_cgroup *to) +static struct obj_cgroup *__get_obj_cgroup_from_memcg(struct mem_cgroup *memcg) { - unsigned short old_id, new_id; + struct obj_cgroup *objcg = NULL; - old_id = mem_cgroup_id(from); - new_id = mem_cgroup_id(to); - - if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) { - mod_memcg_state(from, MEMCG_SWAP, -1); - mod_memcg_state(to, MEMCG_SWAP, 1); - return 0; + for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) { + objcg = rcu_dereference(memcg->objcg); + if (likely(objcg && obj_cgroup_tryget(objcg))) + break; + objcg = NULL; } - return -EINVAL; + return objcg; } -#else -static inline int mem_cgroup_move_swap_account(swp_entry_t entry, - struct mem_cgroup *from, struct mem_cgroup *to) -{ - return -EINVAL; -} -#endif -static DEFINE_MUTEX(memcg_max_mutex); - -static int mem_cgroup_resize_max(struct mem_cgroup *memcg, - unsigned long max, bool memsw) +static struct obj_cgroup *current_objcg_update(void) { - bool enlarge = false; - bool drained = false; - int ret; - bool limits_invariant; - struct page_counter *counter = memsw ? &memcg->memsw : &memcg->memory; + struct mem_cgroup *memcg; + struct obj_cgroup *old, *objcg = NULL; do { - if (signal_pending(current)) { - ret = -EINTR; - break; + /* Atomically drop the update bit. */ + old = xchg(¤t->objcg, NULL); + if (old) { + old = (struct obj_cgroup *) + ((unsigned long)old & ~CURRENT_OBJCG_UPDATE_FLAG); + obj_cgroup_put(old); + + old = NULL; } - mutex_lock(&memcg_max_mutex); + /* If new objcg is NULL, no reason for the second atomic update. */ + if (!current->mm || (current->flags & PF_KTHREAD)) + return NULL; + /* - * Make sure that the new limit (memsw or memory limit) doesn't - * break our basic invariant rule memory.max <= memsw.max. + * Release the objcg pointer from the previous iteration, + * if try_cmpxcg() below fails. */ - limits_invariant = memsw ? max >= memcg->memory.max : - max <= memcg->memsw.max; - if (!limits_invariant) { - mutex_unlock(&memcg_max_mutex); - ret = -EINVAL; - break; + if (unlikely(objcg)) { + obj_cgroup_put(objcg); + objcg = NULL; } - if (max > counter->max) - enlarge = true; - ret = page_counter_set_max(counter, max); - mutex_unlock(&memcg_max_mutex); - if (!ret) - break; - - if (!drained) { - drain_all_stock(memcg); - drained = true; - continue; - } + /* + * Obtain the new objcg pointer. The current task can be + * asynchronously moved to another memcg and the previous + * memcg can be offlined. So let's get the memcg pointer + * and try get a reference to objcg under a rcu read lock. + */ - if (!try_to_free_mem_cgroup_pages(memcg, 1, - GFP_KERNEL, !memsw)) { - ret = -EBUSY; - break; - } - } while (true); + rcu_read_lock(); + memcg = mem_cgroup_from_task(current); + objcg = __get_obj_cgroup_from_memcg(memcg); + rcu_read_unlock(); - if (!ret && enlarge) - memcg_oom_recover(memcg); + /* + * Try set up a new objcg pointer atomically. If it + * fails, it means the update flag was set concurrently, so + * the whole procedure should be repeated. + */ + } while (!try_cmpxchg(¤t->objcg, &old, objcg)); - return ret; + return objcg; } -unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, - gfp_t gfp_mask, - unsigned long *total_scanned) +__always_inline struct obj_cgroup *current_obj_cgroup(void) { - unsigned long nr_reclaimed = 0; - struct mem_cgroup_per_node *mz, *next_mz = NULL; - unsigned long reclaimed; - int loop = 0; - struct mem_cgroup_tree_per_node *mctz; - unsigned long excess; - unsigned long nr_scanned; - - if (order > 0) - return 0; - - mctz = soft_limit_tree_node(pgdat->node_id); - - /* - * Do not even bother to check the largest node if the root - * is empty. Do it lockless to prevent lock bouncing. Races - * are acceptable as soft limit is best effort anyway. - */ - if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root)) - return 0; + struct mem_cgroup *memcg; + struct obj_cgroup *objcg; - /* - * This loop can run a while, specially if mem_cgroup's continuously - * keep exceeding their soft limit and putting the system under - * pressure - */ - do { - if (next_mz) - mz = next_mz; - else - mz = mem_cgroup_largest_soft_limit_node(mctz); - if (!mz) - break; + if (IS_ENABLED(CONFIG_MEMCG_NMI_UNSAFE) && in_nmi()) + return NULL; - nr_scanned = 0; - reclaimed = mem_cgroup_soft_reclaim(mz->memcg, pgdat, - gfp_mask, &nr_scanned); - nr_reclaimed += reclaimed; - *total_scanned += nr_scanned; - spin_lock_irq(&mctz->lock); - __mem_cgroup_remove_exceeded(mz, mctz); + if (in_task()) { + memcg = current->active_memcg; + if (unlikely(memcg)) + goto from_memcg; + objcg = READ_ONCE(current->objcg); + if (unlikely((unsigned long)objcg & CURRENT_OBJCG_UPDATE_FLAG)) + objcg = current_objcg_update(); /* - * If we failed to reclaim anything from this memory cgroup - * it is time to move on to the next cgroup + * Objcg reference is kept by the task, so it's safe + * to use the objcg by the current task. */ - next_mz = NULL; - if (!reclaimed) - next_mz = __mem_cgroup_largest_soft_limit_node(mctz); + return objcg; + } - excess = soft_limit_excess(mz->memcg); - /* - * One school of thought says that we should not add - * back the node to the tree if reclaim returns 0. - * But our reclaim could return 0, simply because due - * to priority we are exposing a smaller subset of - * memory to reclaim from. Consider this as a longer - * term TODO. - */ - /* If excess == 0, no tree ops */ - __mem_cgroup_insert_exceeded(mz, mctz, excess); - spin_unlock_irq(&mctz->lock); - css_put(&mz->memcg->css); - loop++; + memcg = this_cpu_read(int_active_memcg); + if (unlikely(memcg)) + goto from_memcg; + + return NULL; + +from_memcg: + objcg = NULL; + for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) { /* - * Could not reclaim anything and there are no more - * mem cgroups to try or we seem to be looping without - * reclaiming anything. + * Memcg pointer is protected by scope (see set_active_memcg()) + * and is pinning the corresponding objcg, so objcg can't go + * away and can be used within the scope without any additional + * protection. */ - if (!nr_reclaimed && - (next_mz == NULL || - loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS)) + objcg = rcu_dereference_check(memcg->objcg, 1); + if (likely(objcg)) break; - } while (!nr_reclaimed); - if (next_mz) - css_put(&next_mz->memcg->css); - return nr_reclaimed; -} - -/* - * Test whether @memcg has children, dead or alive. Note that this - * function doesn't care whether @memcg has use_hierarchy enabled and - * returns %true if there are child csses according to the cgroup - * hierarchy. Testing use_hierarchy is the caller's responsiblity. - */ -static inline bool memcg_has_children(struct mem_cgroup *memcg) -{ - bool ret; + } - rcu_read_lock(); - ret = css_next_child(NULL, &memcg->css); - rcu_read_unlock(); - return ret; + return objcg; } -/* - * Reclaims as many pages from the given memcg as possible. - * - * Caller is responsible for holding css reference for memcg. - */ -static int mem_cgroup_force_empty(struct mem_cgroup *memcg) +struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio) { - int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; - - /* we call try-to-free pages for make this cgroup empty */ - lru_add_drain_all(); + struct obj_cgroup *objcg; - drain_all_stock(memcg); - - /* try to free all pages in this cgroup */ - while (nr_retries && page_counter_read(&memcg->memory)) { - int progress; + if (!memcg_kmem_online()) + return NULL; - if (signal_pending(current)) - return -EINTR; - - progress = try_to_free_mem_cgroup_pages(memcg, 1, - GFP_KERNEL, true); - if (!progress) { - nr_retries--; - /* maybe some writeback is necessary */ - congestion_wait(BLK_RW_ASYNC, HZ/10); - } + if (folio_memcg_kmem(folio)) { + objcg = __folio_objcg(folio); + obj_cgroup_get(objcg); + } else { + struct mem_cgroup *memcg; + rcu_read_lock(); + memcg = __folio_memcg(folio); + if (memcg) + objcg = __get_obj_cgroup_from_memcg(memcg); + else + objcg = NULL; + rcu_read_unlock(); } - - return 0; + return objcg; } -static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of, - char *buf, size_t nbytes, - loff_t off) +#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC +static inline void account_kmem_nmi_safe(struct mem_cgroup *memcg, int val) { - struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); - - if (mem_cgroup_is_root(memcg)) - return -EINVAL; - return mem_cgroup_force_empty(memcg) ?: nbytes; + if (likely(!in_nmi())) { + mod_memcg_state(memcg, MEMCG_KMEM, val); + } else { + /* preemption is disabled in_nmi(). */ + css_rstat_updated(&memcg->css, smp_processor_id()); + atomic_add(val, &memcg->kmem_stat); + } } - -static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css, - struct cftype *cft) +#else +static inline void account_kmem_nmi_safe(struct mem_cgroup *memcg, int val) { - return mem_cgroup_from_css(css)->use_hierarchy; + mod_memcg_state(memcg, MEMCG_KMEM, val); } +#endif -static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, - struct cftype *cft, u64 val) +/* + * obj_cgroup_uncharge_pages: uncharge a number of kernel pages from a objcg + * @objcg: object cgroup to uncharge + * @nr_pages: number of pages to uncharge + */ +static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg, + unsigned int nr_pages) { - int retval = 0; - struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct mem_cgroup *parent_memcg = mem_cgroup_from_css(memcg->css.parent); + struct mem_cgroup *memcg; - if (memcg->use_hierarchy == val) - return 0; + memcg = get_mem_cgroup_from_objcg(objcg); - /* - * If parent's use_hierarchy is set, we can't make any modifications - * in the child subtrees. If it is unset, then the change can - * occur, provided the current cgroup has no children. - * - * For the root cgroup, parent_mem is NULL, we allow value to be - * set if there are no children. - */ - if ((!parent_memcg || !parent_memcg->use_hierarchy) && - (val == 1 || val == 0)) { - if (!memcg_has_children(memcg)) - memcg->use_hierarchy = val; - else - retval = -EBUSY; - } else - retval = -EINVAL; + account_kmem_nmi_safe(memcg, -nr_pages); + memcg1_account_kmem(memcg, -nr_pages); + if (!mem_cgroup_is_root(memcg)) + refill_stock(memcg, nr_pages); - return retval; + css_put(&memcg->css); } -struct accumulated_stats { - unsigned long stat[MEMCG_NR_STAT]; - unsigned long events[NR_VM_EVENT_ITEMS]; - unsigned long lru_pages[NR_LRU_LISTS]; - const unsigned int *stats_array; - const unsigned int *events_array; - int stats_size; - int events_size; -}; - -static void accumulate_memcg_tree(struct mem_cgroup *memcg, - struct accumulated_stats *acc) +/* + * obj_cgroup_charge_pages: charge a number of kernel pages to a objcg + * @objcg: object cgroup to charge + * @gfp: reclaim mode + * @nr_pages: number of pages to charge + * + * Returns 0 on success, an error code on failure. + */ +static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp, + unsigned int nr_pages) { - struct mem_cgroup *mi; - int i; + struct mem_cgroup *memcg; + int ret; - for_each_mem_cgroup_tree(mi, memcg) { - for (i = 0; i < acc->stats_size; i++) - acc->stat[i] += memcg_page_state(mi, - acc->stats_array ? acc->stats_array[i] : i); + memcg = get_mem_cgroup_from_objcg(objcg); + + ret = try_charge_memcg(memcg, gfp, nr_pages); + if (ret) + goto out; - for (i = 0; i < acc->events_size; i++) - acc->events[i] += memcg_sum_events(mi, - acc->events_array ? acc->events_array[i] : i); + account_kmem_nmi_safe(memcg, nr_pages); + memcg1_account_kmem(memcg, nr_pages); +out: + css_put(&memcg->css); - for (i = 0; i < NR_LRU_LISTS; i++) - acc->lru_pages[i] += - mem_cgroup_nr_lru_pages(mi, BIT(i)); - } + return ret; } -static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) +static struct obj_cgroup *page_objcg(const struct page *page) { - unsigned long val = 0; + unsigned long memcg_data = page->memcg_data; - if (mem_cgroup_is_root(memcg)) { - struct mem_cgroup *iter; + if (mem_cgroup_disabled() || !memcg_data) + return NULL; - for_each_mem_cgroup_tree(iter, memcg) { - val += memcg_page_state(iter, MEMCG_CACHE); - val += memcg_page_state(iter, MEMCG_RSS); - if (swap) - val += memcg_page_state(iter, MEMCG_SWAP); - } - } else { - if (!swap) - val = page_counter_read(&memcg->memory); - else - val = page_counter_read(&memcg->memsw); - } - return val; + VM_BUG_ON_PAGE((memcg_data & OBJEXTS_FLAGS_MASK) != MEMCG_DATA_KMEM, + page); + return (struct obj_cgroup *)(memcg_data - MEMCG_DATA_KMEM); } -enum { - RES_USAGE, - RES_LIMIT, - RES_MAX_USAGE, - RES_FAILCNT, - RES_SOFT_LIMIT, -}; - -static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, - struct cftype *cft) +static void page_set_objcg(struct page *page, const struct obj_cgroup *objcg) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct page_counter *counter; + page->memcg_data = (unsigned long)objcg | MEMCG_DATA_KMEM; +} - switch (MEMFILE_TYPE(cft->private)) { - case _MEM: - counter = &memcg->memory; - break; - case _MEMSWAP: - counter = &memcg->memsw; - break; - case _KMEM: - counter = &memcg->kmem; - break; - case _TCP: - counter = &memcg->tcpmem; - break; - default: - BUG(); - } +/** + * __memcg_kmem_charge_page: charge a kmem page to the current memory cgroup + * @page: page to charge + * @gfp: reclaim mode + * @order: allocation order + * + * Returns 0 on success, an error code on failure. + */ +int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) +{ + struct obj_cgroup *objcg; + int ret = 0; - switch (MEMFILE_ATTR(cft->private)) { - case RES_USAGE: - if (counter == &memcg->memory) - return (u64)mem_cgroup_usage(memcg, false) * PAGE_SIZE; - if (counter == &memcg->memsw) - return (u64)mem_cgroup_usage(memcg, true) * PAGE_SIZE; - return (u64)page_counter_read(counter) * PAGE_SIZE; - case RES_LIMIT: - return (u64)counter->max * PAGE_SIZE; - case RES_MAX_USAGE: - return (u64)counter->watermark * PAGE_SIZE; - case RES_FAILCNT: - return counter->failcnt; - case RES_SOFT_LIMIT: - return (u64)memcg->soft_limit * PAGE_SIZE; - default: - BUG(); + objcg = current_obj_cgroup(); + if (objcg) { + ret = obj_cgroup_charge_pages(objcg, gfp, 1 << order); + if (!ret) { + obj_cgroup_get(objcg); + page_set_objcg(page, objcg); + return 0; + } } + return ret; } -#ifdef CONFIG_MEMCG_KMEM -static int memcg_online_kmem(struct mem_cgroup *memcg) +/** + * __memcg_kmem_uncharge_page: uncharge a kmem page + * @page: page to uncharge + * @order: allocation order + */ +void __memcg_kmem_uncharge_page(struct page *page, int order) { - int memcg_id; - - if (cgroup_memory_nokmem) - return 0; - - BUG_ON(memcg->kmemcg_id >= 0); - BUG_ON(memcg->kmem_state); - - memcg_id = memcg_alloc_cache_id(); - if (memcg_id < 0) - return memcg_id; + struct obj_cgroup *objcg = page_objcg(page); + unsigned int nr_pages = 1 << order; - static_branch_inc(&memcg_kmem_enabled_key); - /* - * A memory cgroup is considered kmem-online as soon as it gets - * kmemcg_id. Setting the id after enabling static branching will - * guarantee no one starts accounting before all call sites are - * patched. - */ - memcg->kmemcg_id = memcg_id; - memcg->kmem_state = KMEM_ONLINE; - INIT_LIST_HEAD(&memcg->kmem_caches); + if (!objcg) + return; - return 0; + obj_cgroup_uncharge_pages(objcg, nr_pages); + page->memcg_data = 0; + obj_cgroup_put(objcg); } -static void memcg_offline_kmem(struct mem_cgroup *memcg) +static void __account_obj_stock(struct obj_cgroup *objcg, + struct obj_stock_pcp *stock, int nr, + struct pglist_data *pgdat, enum node_stat_item idx) { - struct cgroup_subsys_state *css; - struct mem_cgroup *parent, *child; - int kmemcg_id; + int *bytes; - if (memcg->kmem_state != KMEM_ONLINE) - return; /* - * Clear the online state before clearing memcg_caches array - * entries. The slab_mutex in memcg_deactivate_kmem_caches() - * guarantees that no cache will be created for this cgroup - * after we are done (see memcg_create_kmem_cache()). + * Save vmstat data in stock and skip vmstat array update unless + * accumulating over a page of vmstat data or when pgdat changes. */ - memcg->kmem_state = KMEM_ALLOCATED; - - memcg_deactivate_kmem_caches(memcg); - - kmemcg_id = memcg->kmemcg_id; - BUG_ON(kmemcg_id < 0); - - parent = parent_mem_cgroup(memcg); - if (!parent) - parent = root_mem_cgroup; + if (stock->cached_pgdat != pgdat) { + /* Flush the existing cached vmstat data */ + struct pglist_data *oldpg = stock->cached_pgdat; + + if (stock->nr_slab_reclaimable_b) { + mod_objcg_mlstate(objcg, oldpg, NR_SLAB_RECLAIMABLE_B, + stock->nr_slab_reclaimable_b); + stock->nr_slab_reclaimable_b = 0; + } + if (stock->nr_slab_unreclaimable_b) { + mod_objcg_mlstate(objcg, oldpg, NR_SLAB_UNRECLAIMABLE_B, + stock->nr_slab_unreclaimable_b); + stock->nr_slab_unreclaimable_b = 0; + } + stock->cached_pgdat = pgdat; + } + bytes = (idx == NR_SLAB_RECLAIMABLE_B) ? &stock->nr_slab_reclaimable_b + : &stock->nr_slab_unreclaimable_b; /* - * Change kmemcg_id of this cgroup and all its descendants to the - * parent's id, and then move all entries from this cgroup's list_lrus - * to ones of the parent. After we have finished, all list_lrus - * corresponding to this cgroup are guaranteed to remain empty. The - * ordering is imposed by list_lru_node->lock taken by - * memcg_drain_all_list_lrus(). + * Even for large object >= PAGE_SIZE, the vmstat data will still be + * cached locally at least once before pushing it out. */ - rcu_read_lock(); /* can be called from css_free w/o cgroup_mutex */ - css_for_each_descendant_pre(css, &memcg->css) { - child = mem_cgroup_from_css(css); - BUG_ON(child->kmemcg_id != kmemcg_id); - child->kmemcg_id = parent->kmemcg_id; - if (!memcg->use_hierarchy) - break; + if (!*bytes) { + *bytes = nr; + nr = 0; + } else { + *bytes += nr; + if (abs(*bytes) > PAGE_SIZE) { + nr = *bytes; + *bytes = 0; + } else { + nr = 0; + } } - rcu_read_unlock(); - - memcg_drain_all_list_lrus(kmemcg_id, parent); - - memcg_free_cache_id(kmemcg_id); + if (nr) + mod_objcg_mlstate(objcg, pgdat, idx, nr); } -static void memcg_free_kmem(struct mem_cgroup *memcg) +static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes, + struct pglist_data *pgdat, enum node_stat_item idx) { - /* css_alloc() failed, offlining didn't happen */ - if (unlikely(memcg->kmem_state == KMEM_ONLINE)) - memcg_offline_kmem(memcg); + struct obj_stock_pcp *stock; + bool ret = false; - if (memcg->kmem_state == KMEM_ALLOCATED) { - memcg_destroy_kmem_caches(memcg); - static_branch_dec(&memcg_kmem_enabled_key); - WARN_ON(page_counter_read(&memcg->kmem)); + if (!local_trylock(&obj_stock.lock)) + return ret; + + stock = this_cpu_ptr(&obj_stock); + if (objcg == READ_ONCE(stock->cached_objcg) && stock->nr_bytes >= nr_bytes) { + stock->nr_bytes -= nr_bytes; + ret = true; + + if (pgdat) + __account_obj_stock(objcg, stock, nr_bytes, pgdat, idx); } -} -#else -static int memcg_online_kmem(struct mem_cgroup *memcg) -{ - return 0; -} -static void memcg_offline_kmem(struct mem_cgroup *memcg) -{ -} -static void memcg_free_kmem(struct mem_cgroup *memcg) -{ -} -#endif /* CONFIG_MEMCG_KMEM */ -static int memcg_update_kmem_max(struct mem_cgroup *memcg, - unsigned long max) -{ - int ret; + local_unlock(&obj_stock.lock); - mutex_lock(&memcg_max_mutex); - ret = page_counter_set_max(&memcg->kmem, max); - mutex_unlock(&memcg_max_mutex); return ret; } -static int memcg_update_tcp_max(struct mem_cgroup *memcg, unsigned long max) +static void drain_obj_stock(struct obj_stock_pcp *stock) { - int ret; + struct obj_cgroup *old = READ_ONCE(stock->cached_objcg); - mutex_lock(&memcg_max_mutex); + if (!old) + return; - ret = page_counter_set_max(&memcg->tcpmem, max); - if (ret) - goto out; + if (stock->nr_bytes) { + unsigned int nr_pages = stock->nr_bytes >> PAGE_SHIFT; + unsigned int nr_bytes = stock->nr_bytes & (PAGE_SIZE - 1); - if (!memcg->tcpmem_active) { - /* - * The active flag needs to be written after the static_key - * update. This is what guarantees that the socket activation - * function is the last one to run. See mem_cgroup_sk_alloc() - * for details, and note that we don't mark any socket as - * belonging to this memcg until that flag is up. - * - * We need to do this, because static_keys will span multiple - * sites, but we can't control their order. If we mark a socket - * as accounted, but the accounting functions are not patched in - * yet, we'll lose accounting. - * - * We never race with the readers in mem_cgroup_sk_alloc(), - * because when this value change, the code to process it is not - * patched in yet. - */ - static_branch_inc(&memcg_sockets_enabled_key); - memcg->tcpmem_active = true; - } -out: - mutex_unlock(&memcg_max_mutex); - return ret; -} + if (nr_pages) { + struct mem_cgroup *memcg; -/* - * The user of this function is... - * RES_LIMIT. - */ -static ssize_t mem_cgroup_write(struct kernfs_open_file *of, - char *buf, size_t nbytes, loff_t off) -{ - struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); - unsigned long nr_pages; - int ret; + memcg = get_mem_cgroup_from_objcg(old); - buf = strstrip(buf); - ret = page_counter_memparse(buf, "-1", &nr_pages); - if (ret) - return ret; + mod_memcg_state(memcg, MEMCG_KMEM, -nr_pages); + memcg1_account_kmem(memcg, -nr_pages); + if (!mem_cgroup_is_root(memcg)) + memcg_uncharge(memcg, nr_pages); - switch (MEMFILE_ATTR(of_cft(of)->private)) { - case RES_LIMIT: - if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */ - ret = -EINVAL; - break; - } - switch (MEMFILE_TYPE(of_cft(of)->private)) { - case _MEM: - ret = mem_cgroup_resize_max(memcg, nr_pages, false); - break; - case _MEMSWAP: - ret = mem_cgroup_resize_max(memcg, nr_pages, true); - break; - case _KMEM: - ret = memcg_update_kmem_max(memcg, nr_pages); - break; - case _TCP: - ret = memcg_update_tcp_max(memcg, nr_pages); - break; + css_put(&memcg->css); } - break; - case RES_SOFT_LIMIT: - memcg->soft_limit = nr_pages; - ret = 0; - break; - } - return ret ?: nbytes; -} -static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf, - size_t nbytes, loff_t off) -{ - struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); - struct page_counter *counter; - - switch (MEMFILE_TYPE(of_cft(of)->private)) { - case _MEM: - counter = &memcg->memory; - break; - case _MEMSWAP: - counter = &memcg->memsw; - break; - case _KMEM: - counter = &memcg->kmem; - break; - case _TCP: - counter = &memcg->tcpmem; - break; - default: - BUG(); - } - - switch (MEMFILE_ATTR(of_cft(of)->private)) { - case RES_MAX_USAGE: - page_counter_reset_watermark(counter); - break; - case RES_FAILCNT: - counter->failcnt = 0; - break; - default: - BUG(); + /* + * The leftover is flushed to the centralized per-memcg value. + * On the next attempt to refill obj stock it will be moved + * to a per-cpu stock (probably, on an other CPU), see + * refill_obj_stock(). + * + * How often it's flushed is a trade-off between the memory + * limit enforcement accuracy and potential CPU contention, + * so it might be changed in the future. + */ + atomic_add(nr_bytes, &old->nr_charged_bytes); + stock->nr_bytes = 0; } - return nbytes; -} - -static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css, - struct cftype *cft) -{ - return mem_cgroup_from_css(css)->move_charge_at_immigrate; -} - -#ifdef CONFIG_MMU -static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, - struct cftype *cft, u64 val) -{ - struct mem_cgroup *memcg = mem_cgroup_from_css(css); - - if (val & ~MOVE_MASK) - return -EINVAL; - /* - * No kind of locking is needed in here, because ->can_attach() will - * check this value once in the beginning of the process, and then carry - * on with stale data. This means that changes to this value will only - * affect task migrations starting after the change. + * Flush the vmstat data in current stock */ - memcg->move_charge_at_immigrate = val; - return 0; -} -#else -static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, - struct cftype *cft, u64 val) -{ - return -ENOSYS; -} -#endif - -#ifdef CONFIG_NUMA -static int memcg_numa_stat_show(struct seq_file *m, void *v) -{ - struct numa_stat { - const char *name; - unsigned int lru_mask; - }; - - static const struct numa_stat stats[] = { - { "total", LRU_ALL }, - { "file", LRU_ALL_FILE }, - { "anon", LRU_ALL_ANON }, - { "unevictable", BIT(LRU_UNEVICTABLE) }, - }; - const struct numa_stat *stat; - int nid; - unsigned long nr; - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - - for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) { - nr = mem_cgroup_nr_lru_pages(memcg, stat->lru_mask); - seq_printf(m, "%s=%lu", stat->name, nr); - for_each_node_state(nid, N_MEMORY) { - nr = mem_cgroup_node_nr_lru_pages(memcg, nid, - stat->lru_mask); - seq_printf(m, " N%d=%lu", nid, nr); + if (stock->nr_slab_reclaimable_b || stock->nr_slab_unreclaimable_b) { + if (stock->nr_slab_reclaimable_b) { + mod_objcg_mlstate(old, stock->cached_pgdat, + NR_SLAB_RECLAIMABLE_B, + stock->nr_slab_reclaimable_b); + stock->nr_slab_reclaimable_b = 0; } - seq_putc(m, '\n'); - } - - for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) { - struct mem_cgroup *iter; - - nr = 0; - for_each_mem_cgroup_tree(iter, memcg) - nr += mem_cgroup_nr_lru_pages(iter, stat->lru_mask); - seq_printf(m, "hierarchical_%s=%lu", stat->name, nr); - for_each_node_state(nid, N_MEMORY) { - nr = 0; - for_each_mem_cgroup_tree(iter, memcg) - nr += mem_cgroup_node_nr_lru_pages( - iter, nid, stat->lru_mask); - seq_printf(m, " N%d=%lu", nid, nr); + if (stock->nr_slab_unreclaimable_b) { + mod_objcg_mlstate(old, stock->cached_pgdat, + NR_SLAB_UNRECLAIMABLE_B, + stock->nr_slab_unreclaimable_b); + stock->nr_slab_unreclaimable_b = 0; } - seq_putc(m, '\n'); + stock->cached_pgdat = NULL; } - return 0; + WRITE_ONCE(stock->cached_objcg, NULL); + obj_cgroup_put(old); } -#endif /* CONFIG_NUMA */ -/* Universal VM events cgroup1 shows, original sort order */ -static const unsigned int memcg1_events[] = { - PGPGIN, - PGPGOUT, - PGFAULT, - PGMAJFAULT, -}; - -static const char *const memcg1_event_names[] = { - "pgpgin", - "pgpgout", - "pgfault", - "pgmajfault", -}; - -static int memcg_stat_show(struct seq_file *m, void *v) +static bool obj_stock_flush_required(struct obj_stock_pcp *stock, + struct mem_cgroup *root_memcg) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - unsigned long memory, memsw; - struct mem_cgroup *mi; - unsigned int i; - struct accumulated_stats acc; - - BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats)); - BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); + struct obj_cgroup *objcg = READ_ONCE(stock->cached_objcg); + struct mem_cgroup *memcg; + bool flush = false; - for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { - if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) - continue; - seq_printf(m, "%s %lu\n", memcg1_stat_names[i], - memcg_page_state(memcg, memcg1_stats[i]) * - PAGE_SIZE); + rcu_read_lock(); + if (objcg) { + memcg = obj_cgroup_memcg(objcg); + if (memcg && mem_cgroup_is_descendant(memcg, root_memcg)) + flush = true; } + rcu_read_unlock(); - for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) - seq_printf(m, "%s %lu\n", memcg1_event_names[i], - memcg_sum_events(memcg, memcg1_events[i])); + return flush; +} - for (i = 0; i < NR_LRU_LISTS; i++) - seq_printf(m, "%s %lu\n", mem_cgroup_lru_names[i], - mem_cgroup_nr_lru_pages(memcg, BIT(i)) * PAGE_SIZE); +static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes, + bool allow_uncharge, int nr_acct, struct pglist_data *pgdat, + enum node_stat_item idx) +{ + struct obj_stock_pcp *stock; + unsigned int nr_pages = 0; - /* Hierarchical information */ - memory = memsw = PAGE_COUNTER_MAX; - for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) { - memory = min(memory, mi->memory.max); - memsw = min(memsw, mi->memsw.max); - } - seq_printf(m, "hierarchical_memory_limit %llu\n", - (u64)memory * PAGE_SIZE); - if (do_memsw_account()) - seq_printf(m, "hierarchical_memsw_limit %llu\n", - (u64)memsw * PAGE_SIZE); - - memset(&acc, 0, sizeof(acc)); - acc.stats_size = ARRAY_SIZE(memcg1_stats); - acc.stats_array = memcg1_stats; - acc.events_size = ARRAY_SIZE(memcg1_events); - acc.events_array = memcg1_events; - accumulate_memcg_tree(memcg, &acc); - - for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { - if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) - continue; - seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i], - (u64)acc.stat[i] * PAGE_SIZE); + if (!local_trylock(&obj_stock.lock)) { + if (pgdat) + mod_objcg_mlstate(objcg, pgdat, idx, nr_bytes); + nr_pages = nr_bytes >> PAGE_SHIFT; + nr_bytes = nr_bytes & (PAGE_SIZE - 1); + atomic_add(nr_bytes, &objcg->nr_charged_bytes); + goto out; } - for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) - seq_printf(m, "total_%s %llu\n", memcg1_event_names[i], - (u64)acc.events[i]); - - for (i = 0; i < NR_LRU_LISTS; i++) - seq_printf(m, "total_%s %llu\n", mem_cgroup_lru_names[i], - (u64)acc.lru_pages[i] * PAGE_SIZE); + stock = this_cpu_ptr(&obj_stock); + if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */ + drain_obj_stock(stock); + obj_cgroup_get(objcg); + stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes) + ? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0; + WRITE_ONCE(stock->cached_objcg, objcg); -#ifdef CONFIG_DEBUG_VM - { - pg_data_t *pgdat; - struct mem_cgroup_per_node *mz; - struct zone_reclaim_stat *rstat; - unsigned long recent_rotated[2] = {0, 0}; - unsigned long recent_scanned[2] = {0, 0}; - - for_each_online_pgdat(pgdat) { - mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id); - rstat = &mz->lruvec.reclaim_stat; - - recent_rotated[0] += rstat->recent_rotated[0]; - recent_rotated[1] += rstat->recent_rotated[1]; - recent_scanned[0] += rstat->recent_scanned[0]; - recent_scanned[1] += rstat->recent_scanned[1]; - } - seq_printf(m, "recent_rotated_anon %lu\n", recent_rotated[0]); - seq_printf(m, "recent_rotated_file %lu\n", recent_rotated[1]); - seq_printf(m, "recent_scanned_anon %lu\n", recent_scanned[0]); - seq_printf(m, "recent_scanned_file %lu\n", recent_scanned[1]); + allow_uncharge = true; /* Allow uncharge when objcg changes */ } -#endif - - return 0; -} - -static u64 mem_cgroup_swappiness_read(struct cgroup_subsys_state *css, - struct cftype *cft) -{ - struct mem_cgroup *memcg = mem_cgroup_from_css(css); - - return mem_cgroup_swappiness(memcg); -} - -static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css, - struct cftype *cft, u64 val) -{ - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + stock->nr_bytes += nr_bytes; - if (val > 100) - return -EINVAL; + if (pgdat) + __account_obj_stock(objcg, stock, nr_acct, pgdat, idx); - if (css->parent) - memcg->swappiness = val; - else - vm_swappiness = val; + if (allow_uncharge && (stock->nr_bytes > PAGE_SIZE)) { + nr_pages = stock->nr_bytes >> PAGE_SHIFT; + stock->nr_bytes &= (PAGE_SIZE - 1); + } - return 0; + local_unlock(&obj_stock.lock); +out: + if (nr_pages) + obj_cgroup_uncharge_pages(objcg, nr_pages); } -static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap) +static int obj_cgroup_charge_account(struct obj_cgroup *objcg, gfp_t gfp, size_t size, + struct pglist_data *pgdat, enum node_stat_item idx) { - struct mem_cgroup_threshold_ary *t; - unsigned long usage; - int i; - - rcu_read_lock(); - if (!swap) - t = rcu_dereference(memcg->thresholds.primary); - else - t = rcu_dereference(memcg->memsw_thresholds.primary); - - if (!t) - goto unlock; - - usage = mem_cgroup_usage(memcg, swap); - - /* - * current_threshold points to threshold just below or equal to usage. - * If it's not true, a threshold was crossed after last - * call of __mem_cgroup_threshold(). - */ - i = t->current_threshold; - - /* - * Iterate backward over array of thresholds starting from - * current_threshold and check if a threshold is crossed. - * If none of thresholds below usage is crossed, we read - * only one element of the array here. - */ - for (; i >= 0 && unlikely(t->entries[i].threshold > usage); i--) - eventfd_signal(t->entries[i].eventfd, 1); + unsigned int nr_pages, nr_bytes; + int ret; - /* i = current_threshold + 1 */ - i++; + if (likely(consume_obj_stock(objcg, size, pgdat, idx))) + return 0; /* - * Iterate forward over array of thresholds starting from - * current_threshold+1 and check if a threshold is crossed. - * If none of thresholds above usage is crossed, we read - * only one element of the array here. + * In theory, objcg->nr_charged_bytes can have enough + * pre-charged bytes to satisfy the allocation. However, + * flushing objcg->nr_charged_bytes requires two atomic + * operations, and objcg->nr_charged_bytes can't be big. + * The shared objcg->nr_charged_bytes can also become a + * performance bottleneck if all tasks of the same memcg are + * trying to update it. So it's better to ignore it and try + * grab some new pages. The stock's nr_bytes will be flushed to + * objcg->nr_charged_bytes later on when objcg changes. + * + * The stock's nr_bytes may contain enough pre-charged bytes + * to allow one less page from being charged, but we can't rely + * on the pre-charged bytes not being changed outside of + * consume_obj_stock() or refill_obj_stock(). So ignore those + * pre-charged bytes as well when charging pages. To avoid a + * page uncharge right after a page charge, we set the + * allow_uncharge flag to false when calling refill_obj_stock() + * to temporarily allow the pre-charged bytes to exceed the page + * size limit. The maximum reachable value of the pre-charged + * bytes is (sizeof(object) + PAGE_SIZE - 2) if there is no data + * race. */ - for (; i < t->size && unlikely(t->entries[i].threshold <= usage); i++) - eventfd_signal(t->entries[i].eventfd, 1); + nr_pages = size >> PAGE_SHIFT; + nr_bytes = size & (PAGE_SIZE - 1); - /* Update current_threshold */ - t->current_threshold = i - 1; -unlock: - rcu_read_unlock(); -} + if (nr_bytes) + nr_pages += 1; -static void mem_cgroup_threshold(struct mem_cgroup *memcg) -{ - while (memcg) { - __mem_cgroup_threshold(memcg, false); - if (do_memsw_account()) - __mem_cgroup_threshold(memcg, true); + ret = obj_cgroup_charge_pages(objcg, gfp, nr_pages); + if (!ret && (nr_bytes || pgdat)) + refill_obj_stock(objcg, nr_bytes ? PAGE_SIZE - nr_bytes : 0, + false, size, pgdat, idx); - memcg = parent_mem_cgroup(memcg); - } + return ret; } -static int compare_thresholds(const void *a, const void *b) +int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size) { - const struct mem_cgroup_threshold *_a = a; - const struct mem_cgroup_threshold *_b = b; - - if (_a->threshold > _b->threshold) - return 1; - - if (_a->threshold < _b->threshold) - return -1; - - return 0; + return obj_cgroup_charge_account(objcg, gfp, size, NULL, 0); } -static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg) +void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size) { - struct mem_cgroup_eventfd_list *ev; - - spin_lock(&memcg_oom_lock); - - list_for_each_entry(ev, &memcg->oom_notify, list) - eventfd_signal(ev->eventfd, 1); - - spin_unlock(&memcg_oom_lock); - return 0; + refill_obj_stock(objcg, size, true, 0, NULL, 0); } -static void mem_cgroup_oom_notify(struct mem_cgroup *memcg) +static inline size_t obj_full_size(struct kmem_cache *s) { - struct mem_cgroup *iter; - - for_each_mem_cgroup_tree(iter, memcg) - mem_cgroup_oom_notify_cb(iter); + /* + * For each accounted object there is an extra space which is used + * to store obj_cgroup membership. Charge it too. + */ + return s->size + sizeof(struct obj_cgroup *); } -static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg, - struct eventfd_ctx *eventfd, const char *args, enum res_type type) +bool __memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru, + gfp_t flags, size_t size, void **p) { - struct mem_cgroup_thresholds *thresholds; - struct mem_cgroup_threshold_ary *new; - unsigned long threshold; - unsigned long usage; - int i, size, ret; - - ret = page_counter_memparse(args, "-1", &threshold); - if (ret) - return ret; + struct obj_cgroup *objcg; + struct slab *slab; + unsigned long off; + size_t i; - mutex_lock(&memcg->thresholds_lock); + /* + * The obtained objcg pointer is safe to use within the current scope, + * defined by current task or set_active_memcg() pair. + * obj_cgroup_get() is used to get a permanent reference. + */ + objcg = current_obj_cgroup(); + if (!objcg) + return true; - if (type == _MEM) { - thresholds = &memcg->thresholds; - usage = mem_cgroup_usage(memcg, false); - } else if (type == _MEMSWAP) { - thresholds = &memcg->memsw_thresholds; - usage = mem_cgroup_usage(memcg, true); - } else - BUG(); + /* + * slab_alloc_node() avoids the NULL check, so we might be called with a + * single NULL object. kmem_cache_alloc_bulk() aborts if it can't fill + * the whole requested size. + * return success as there's nothing to free back + */ + if (unlikely(*p == NULL)) + return true; - /* Check if a threshold crossed before adding a new one */ - if (thresholds->primary) - __mem_cgroup_threshold(memcg, type == _MEMSWAP); + flags &= gfp_allowed_mask; - size = thresholds->primary ? thresholds->primary->size + 1 : 1; + if (lru) { + int ret; + struct mem_cgroup *memcg; - /* Allocate memory for new array of thresholds */ - new = kmalloc(sizeof(*new) + size * sizeof(struct mem_cgroup_threshold), - GFP_KERNEL); - if (!new) { - ret = -ENOMEM; - goto unlock; - } - new->size = size; + memcg = get_mem_cgroup_from_objcg(objcg); + ret = memcg_list_lru_alloc(memcg, lru, flags); + css_put(&memcg->css); - /* Copy thresholds (if any) to new array */ - if (thresholds->primary) { - memcpy(new->entries, thresholds->primary->entries, (size - 1) * - sizeof(struct mem_cgroup_threshold)); + if (ret) + return false; } - /* Add new threshold */ - new->entries[size - 1].eventfd = eventfd; - new->entries[size - 1].threshold = threshold; - - /* Sort thresholds. Registering of new threshold isn't time-critical */ - sort(new->entries, size, sizeof(struct mem_cgroup_threshold), - compare_thresholds, NULL); - - /* Find current threshold */ - new->current_threshold = -1; for (i = 0; i < size; i++) { - if (new->entries[i].threshold <= usage) { - /* - * new->current_threshold will not be used until - * rcu_assign_pointer(), so it's safe to increment - * it here. - */ - ++new->current_threshold; - } else - break; - } - - /* Free old spare buffer and save old primary buffer as spare */ - kfree(thresholds->spare); - thresholds->spare = thresholds->primary; - - rcu_assign_pointer(thresholds->primary, new); + slab = virt_to_slab(p[i]); - /* To be sure that nobody uses thresholds */ - synchronize_rcu(); + if (!slab_obj_exts(slab) && + alloc_slab_obj_exts(slab, s, flags, false)) { + continue; + } -unlock: - mutex_unlock(&memcg->thresholds_lock); + /* + * if we fail and size is 1, memcg_alloc_abort_single() will + * just free the object, which is ok as we have not assigned + * objcg to its obj_ext yet + * + * for larger sizes, kmem_cache_free_bulk() will uncharge + * any objects that were already charged and obj_ext assigned + * + * TODO: we could batch this until slab_pgdat(slab) changes + * between iterations, with a more complicated undo + */ + if (obj_cgroup_charge_account(objcg, flags, obj_full_size(s), + slab_pgdat(slab), cache_vmstat_idx(s))) + return false; - return ret; -} + off = obj_to_index(s, slab, p[i]); + obj_cgroup_get(objcg); + slab_obj_exts(slab)[off].objcg = objcg; + } -static int mem_cgroup_usage_register_event(struct mem_cgroup *memcg, - struct eventfd_ctx *eventfd, const char *args) -{ - return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEM); + return true; } -static int memsw_cgroup_usage_register_event(struct mem_cgroup *memcg, - struct eventfd_ctx *eventfd, const char *args) +void __memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, + void **p, int objects, struct slabobj_ext *obj_exts) { - return __mem_cgroup_usage_register_event(memcg, eventfd, args, _MEMSWAP); -} + size_t obj_size = obj_full_size(s); -static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, - struct eventfd_ctx *eventfd, enum res_type type) -{ - struct mem_cgroup_thresholds *thresholds; - struct mem_cgroup_threshold_ary *new; - unsigned long usage; - int i, j, size; + for (int i = 0; i < objects; i++) { + struct obj_cgroup *objcg; + unsigned int off; - mutex_lock(&memcg->thresholds_lock); - - if (type == _MEM) { - thresholds = &memcg->thresholds; - usage = mem_cgroup_usage(memcg, false); - } else if (type == _MEMSWAP) { - thresholds = &memcg->memsw_thresholds; - usage = mem_cgroup_usage(memcg, true); - } else - BUG(); - - if (!thresholds->primary) - goto unlock; - - /* Check if a threshold crossed before removing */ - __mem_cgroup_threshold(memcg, type == _MEMSWAP); + off = obj_to_index(s, slab, p[i]); + objcg = obj_exts[off].objcg; + if (!objcg) + continue; - /* Calculate new number of threshold */ - size = 0; - for (i = 0; i < thresholds->primary->size; i++) { - if (thresholds->primary->entries[i].eventfd != eventfd) - size++; + obj_exts[off].objcg = NULL; + refill_obj_stock(objcg, obj_size, true, -obj_size, + slab_pgdat(slab), cache_vmstat_idx(s)); + obj_cgroup_put(objcg); } +} - new = thresholds->spare; +/* + * The objcg is only set on the first page, so transfer it to all the + * other pages. + */ +void split_page_memcg(struct page *page, unsigned order) +{ + struct obj_cgroup *objcg = page_objcg(page); + unsigned int i, nr = 1 << order; - /* Set thresholds array to NULL if we don't have thresholds */ - if (!size) { - kfree(new); - new = NULL; - goto swap_buffers; - } + if (!objcg) + return; - new->size = size; + for (i = 1; i < nr; i++) + page_set_objcg(&page[i], objcg); - /* Copy thresholds and find current threshold */ - new->current_threshold = -1; - for (i = 0, j = 0; i < thresholds->primary->size; i++) { - if (thresholds->primary->entries[i].eventfd == eventfd) - continue; + obj_cgroup_get_many(objcg, nr - 1); +} - new->entries[j] = thresholds->primary->entries[i]; - if (new->entries[j].threshold <= usage) { - /* - * new->current_threshold will not be used - * until rcu_assign_pointer(), so it's safe to increment - * it here. - */ - ++new->current_threshold; - } - j++; - } +void folio_split_memcg_refs(struct folio *folio, unsigned old_order, + unsigned new_order) +{ + unsigned new_refs; -swap_buffers: - /* Swap primary and spare array */ - thresholds->spare = thresholds->primary; + if (mem_cgroup_disabled() || !folio_memcg_charged(folio)) + return; - rcu_assign_pointer(thresholds->primary, new); + new_refs = (1 << (old_order - new_order)) - 1; + css_get_many(&__folio_memcg(folio)->css, new_refs); +} - /* To be sure that nobody uses thresholds */ - synchronize_rcu(); +unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) +{ + unsigned long val; - /* If all events are unregistered, free the spare array */ - if (!new) { - kfree(thresholds->spare); - thresholds->spare = NULL; + if (mem_cgroup_is_root(memcg)) { + /* + * Approximate root's usage from global state. This isn't + * perfect, but the root usage was always an approximation. + */ + val = global_node_page_state(NR_FILE_PAGES) + + global_node_page_state(NR_ANON_MAPPED); + if (swap) + val += total_swap_pages - get_nr_swap_pages(); + } else { + if (!swap) + val = page_counter_read(&memcg->memory); + else + val = page_counter_read(&memcg->memsw); } -unlock: - mutex_unlock(&memcg->thresholds_lock); + return val; } -static void mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, - struct eventfd_ctx *eventfd) +static int memcg_online_kmem(struct mem_cgroup *memcg) { - return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEM); -} + struct obj_cgroup *objcg; -static void memsw_cgroup_usage_unregister_event(struct mem_cgroup *memcg, - struct eventfd_ctx *eventfd) -{ - return __mem_cgroup_usage_unregister_event(memcg, eventfd, _MEMSWAP); -} + if (mem_cgroup_kmem_disabled()) + return 0; -static int mem_cgroup_oom_register_event(struct mem_cgroup *memcg, - struct eventfd_ctx *eventfd, const char *args) -{ - struct mem_cgroup_eventfd_list *event; + if (unlikely(mem_cgroup_is_root(memcg))) + return 0; - event = kmalloc(sizeof(*event), GFP_KERNEL); - if (!event) + objcg = obj_cgroup_alloc(); + if (!objcg) return -ENOMEM; - spin_lock(&memcg_oom_lock); + objcg->memcg = memcg; + rcu_assign_pointer(memcg->objcg, objcg); + obj_cgroup_get(objcg); + memcg->orig_objcg = objcg; - event->eventfd = eventfd; - list_add(&event->list, &memcg->oom_notify); + static_branch_enable(&memcg_kmem_online_key); - /* already in OOM ? */ - if (memcg->under_oom) - eventfd_signal(eventfd, 1); - spin_unlock(&memcg_oom_lock); + memcg->kmemcg_id = memcg->id.id; return 0; } -static void mem_cgroup_oom_unregister_event(struct mem_cgroup *memcg, - struct eventfd_ctx *eventfd) -{ - struct mem_cgroup_eventfd_list *ev, *tmp; - - spin_lock(&memcg_oom_lock); - - list_for_each_entry_safe(ev, tmp, &memcg->oom_notify, list) { - if (ev->eventfd == eventfd) { - list_del(&ev->list); - kfree(ev); - } - } - - spin_unlock(&memcg_oom_lock); -} - -static int mem_cgroup_oom_control_read(struct seq_file *sf, void *v) +static void memcg_offline_kmem(struct mem_cgroup *memcg) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(sf)); + struct mem_cgroup *parent; - seq_printf(sf, "oom_kill_disable %d\n", memcg->oom_kill_disable); - seq_printf(sf, "under_oom %d\n", (bool)memcg->under_oom); - seq_printf(sf, "oom_kill %lu\n", - atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL])); - return 0; -} + if (mem_cgroup_kmem_disabled()) + return; -static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css, - struct cftype *cft, u64 val) -{ - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + if (unlikely(mem_cgroup_is_root(memcg))) + return; - /* cannot set to root cgroup and only 0 and 1 are allowed */ - if (!css->parent || !((val == 0) || (val == 1))) - return -EINVAL; + parent = parent_mem_cgroup(memcg); + if (!parent) + parent = root_mem_cgroup; - memcg->oom_kill_disable = val; - if (!val) - memcg_oom_recover(memcg); + memcg_reparent_list_lrus(memcg, parent); - return 0; + /* + * Objcg's reparenting must be after list_lru's, make sure list_lru + * helpers won't use parent's list_lru until child is drained. + */ + memcg_reparent_objcgs(memcg, parent); } #ifdef CONFIG_CGROUP_WRITEBACK +#include <trace/events/writeback.h> + static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp) { return wb_domain_init(&memcg->cgwb_domain, gfp); @@ -3898,16 +3397,17 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); struct mem_cgroup *parent; - *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY); + mem_cgroup_flush_stats_ratelimited(memcg); - /* this should eventually include NR_UNSTABLE_NFS */ + *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY); *pwriteback = memcg_page_state(memcg, NR_WRITEBACK); - *pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) | - (1 << LRU_ACTIVE_FILE)); - *pheadroom = PAGE_COUNTER_MAX; + *pfilepages = memcg_page_state(memcg, NR_INACTIVE_FILE) + + memcg_page_state(memcg, NR_ACTIVE_FILE); + *pheadroom = PAGE_COUNTER_MAX; while ((parent = parent_mem_cgroup(memcg))) { - unsigned long ceiling = min(memcg->memory.max, memcg->high); + unsigned long ceiling = min(READ_ONCE(memcg->memory.max), + READ_ONCE(memcg->memory.high)); unsigned long used = page_counter_read(&memcg->memory); *pheadroom = min(*pheadroom, ceiling - min(ceiling, used)); @@ -3915,376 +3415,146 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, } } -#else /* CONFIG_CGROUP_WRITEBACK */ - -static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp) -{ - return 0; -} - -static void memcg_wb_domain_exit(struct mem_cgroup *memcg) -{ -} - -static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg) -{ -} - -#endif /* CONFIG_CGROUP_WRITEBACK */ - /* - * DO NOT USE IN NEW FILES. + * Foreign dirty flushing * - * "cgroup.event_control" implementation. + * There's an inherent mismatch between memcg and writeback. The former + * tracks ownership per-page while the latter per-inode. This was a + * deliberate design decision because honoring per-page ownership in the + * writeback path is complicated, may lead to higher CPU and IO overheads + * and deemed unnecessary given that write-sharing an inode across + * different cgroups isn't a common use-case. * - * This is way over-engineered. It tries to support fully configurable - * events for each user. Such level of flexibility is completely - * unnecessary especially in the light of the planned unified hierarchy. + * Combined with inode majority-writer ownership switching, this works well + * enough in most cases but there are some pathological cases. For + * example, let's say there are two cgroups A and B which keep writing to + * different but confined parts of the same inode. B owns the inode and + * A's memory is limited far below B's. A's dirty ratio can rise enough to + * trigger balance_dirty_pages() sleeps but B's can be low enough to avoid + * triggering background writeback. A will be slowed down without a way to + * make writeback of the dirty pages happen. * - * Please deprecate this and replace with something simpler if at all - * possible. - */ - -/* - * Unregister event and free resources. + * Conditions like the above can lead to a cgroup getting repeatedly and + * severely throttled after making some progress after each + * dirty_expire_interval while the underlying IO device is almost + * completely idle. + * + * Solving this problem completely requires matching the ownership tracking + * granularities between memcg and writeback in either direction. However, + * the more egregious behaviors can be avoided by simply remembering the + * most recent foreign dirtying events and initiating remote flushes on + * them when local writeback isn't enough to keep the memory clean enough. * - * Gets called from workqueue. + * The following two functions implement such mechanism. When a foreign + * page - a page whose memcg and writeback ownerships don't match - is + * dirtied, mem_cgroup_track_foreign_dirty() records the inode owning + * bdi_writeback on the page owning memcg. When balance_dirty_pages() + * decides that the memcg needs to sleep due to high dirty ratio, it calls + * mem_cgroup_flush_foreign() which queues writeback on the recorded + * foreign bdi_writebacks which haven't expired. Both the numbers of + * recorded bdi_writebacks and concurrent in-flight foreign writebacks are + * limited to MEMCG_CGWB_FRN_CNT. + * + * The mechanism only remembers IDs and doesn't hold any object references. + * As being wrong occasionally doesn't matter, updates and accesses to the + * records are lockless and racy. */ -static void memcg_event_remove(struct work_struct *work) -{ - struct mem_cgroup_event *event = - container_of(work, struct mem_cgroup_event, remove); - struct mem_cgroup *memcg = event->memcg; +void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, + struct bdi_writeback *wb) +{ + struct mem_cgroup *memcg = folio_memcg(folio); + struct memcg_cgwb_frn *frn; + u64 now = get_jiffies_64(); + u64 oldest_at = now; + int oldest = -1; + int i; - remove_wait_queue(event->wqh, &event->wait); + trace_track_foreign_dirty(folio, wb); - event->unregister_event(memcg, event->eventfd); + /* + * Pick the slot to use. If there is already a slot for @wb, keep + * using it. If not replace the oldest one which isn't being + * written out. + */ + for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) { + frn = &memcg->cgwb_frn[i]; + if (frn->bdi_id == wb->bdi->id && + frn->memcg_id == wb->memcg_css->id) + break; + if (time_before64(frn->at, oldest_at) && + atomic_read(&frn->done.cnt) == 1) { + oldest = i; + oldest_at = frn->at; + } + } - /* Notify userspace the event is going away. */ - eventfd_signal(event->eventfd, 1); + if (i < MEMCG_CGWB_FRN_CNT) { + /* + * Re-using an existing one. Update timestamp lazily to + * avoid making the cacheline hot. We want them to be + * reasonably up-to-date and significantly shorter than + * dirty_expire_interval as that's what expires the record. + * Use the shorter of 1s and dirty_expire_interval / 8. + */ + unsigned long update_intv = + min_t(unsigned long, HZ, + msecs_to_jiffies(dirty_expire_interval * 10) / 8); - eventfd_ctx_put(event->eventfd); - kfree(event); - css_put(&memcg->css); + if (time_before64(frn->at, now - update_intv)) + frn->at = now; + } else if (oldest >= 0) { + /* replace the oldest free one */ + frn = &memcg->cgwb_frn[oldest]; + frn->bdi_id = wb->bdi->id; + frn->memcg_id = wb->memcg_css->id; + frn->at = now; + } } -/* - * Gets called on EPOLLHUP on eventfd when user closes it. - * - * Called with wqh->lock held and interrupts disabled. - */ -static int memcg_event_wake(wait_queue_entry_t *wait, unsigned mode, - int sync, void *key) +/* issue foreign writeback flushes for recorded foreign dirtying events */ +void mem_cgroup_flush_foreign(struct bdi_writeback *wb) { - struct mem_cgroup_event *event = - container_of(wait, struct mem_cgroup_event, wait); - struct mem_cgroup *memcg = event->memcg; - __poll_t flags = key_to_poll(key); + struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); + unsigned long intv = msecs_to_jiffies(dirty_expire_interval * 10); + u64 now = jiffies_64; + int i; + + for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) { + struct memcg_cgwb_frn *frn = &memcg->cgwb_frn[i]; - if (flags & EPOLLHUP) { /* - * If the event has been detached at cgroup removal, we - * can simply return knowing the other side will cleanup - * for us. - * - * We can't race against event freeing since the other - * side will require wqh->lock via remove_wait_queue(), - * which we hold. + * If the record is older than dirty_expire_interval, + * writeback on it has already started. No need to kick it + * off again. Also, don't start a new one if there's + * already one in flight. */ - spin_lock(&memcg->event_list_lock); - if (!list_empty(&event->list)) { - list_del_init(&event->list); - /* - * We are in atomic context, but cgroup_event_remove() - * may sleep, so we have to call it in workqueue. - */ - schedule_work(&event->remove); + if (time_after64(frn->at, now - intv) && + atomic_read(&frn->done.cnt) == 1) { + frn->at = 0; + trace_flush_foreign(wb, frn->bdi_id, frn->memcg_id); + cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id, + WB_REASON_FOREIGN_FLUSH, + &frn->done); } - spin_unlock(&memcg->event_list_lock); } +} +#else /* CONFIG_CGROUP_WRITEBACK */ + +static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp) +{ return 0; } -static void memcg_event_ptable_queue_proc(struct file *file, - wait_queue_head_t *wqh, poll_table *pt) +static void memcg_wb_domain_exit(struct mem_cgroup *memcg) { - struct mem_cgroup_event *event = - container_of(pt, struct mem_cgroup_event, pt); - - event->wqh = wqh; - add_wait_queue(wqh, &event->wait); } -/* - * DO NOT USE IN NEW FILES. - * - * Parse input and register new cgroup event handler. - * - * Input must be in format '<event_fd> <control_fd> <args>'. - * Interpretation of args is defined by control file implementation. - */ -static ssize_t memcg_write_event_control(struct kernfs_open_file *of, - char *buf, size_t nbytes, loff_t off) +static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg) { - struct cgroup_subsys_state *css = of_css(of); - struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct mem_cgroup_event *event; - struct cgroup_subsys_state *cfile_css; - unsigned int efd, cfd; - struct fd efile; - struct fd cfile; - const char *name; - char *endp; - int ret; - - buf = strstrip(buf); - - efd = simple_strtoul(buf, &endp, 10); - if (*endp != ' ') - return -EINVAL; - buf = endp + 1; - - cfd = simple_strtoul(buf, &endp, 10); - if ((*endp != ' ') && (*endp != '\0')) - return -EINVAL; - buf = endp + 1; - - event = kzalloc(sizeof(*event), GFP_KERNEL); - if (!event) - return -ENOMEM; - - event->memcg = memcg; - INIT_LIST_HEAD(&event->list); - init_poll_funcptr(&event->pt, memcg_event_ptable_queue_proc); - init_waitqueue_func_entry(&event->wait, memcg_event_wake); - INIT_WORK(&event->remove, memcg_event_remove); - - efile = fdget(efd); - if (!efile.file) { - ret = -EBADF; - goto out_kfree; - } - - event->eventfd = eventfd_ctx_fileget(efile.file); - if (IS_ERR(event->eventfd)) { - ret = PTR_ERR(event->eventfd); - goto out_put_efile; - } - - cfile = fdget(cfd); - if (!cfile.file) { - ret = -EBADF; - goto out_put_eventfd; - } - - /* the process need read permission on control file */ - /* AV: shouldn't we check that it's been opened for read instead? */ - ret = inode_permission(file_inode(cfile.file), MAY_READ); - if (ret < 0) - goto out_put_cfile; - - /* - * Determine the event callbacks and set them in @event. This used - * to be done via struct cftype but cgroup core no longer knows - * about these events. The following is crude but the whole thing - * is for compatibility anyway. - * - * DO NOT ADD NEW FILES. - */ - name = cfile.file->f_path.dentry->d_name.name; - - if (!strcmp(name, "memory.usage_in_bytes")) { - event->register_event = mem_cgroup_usage_register_event; - event->unregister_event = mem_cgroup_usage_unregister_event; - } else if (!strcmp(name, "memory.oom_control")) { - event->register_event = mem_cgroup_oom_register_event; - event->unregister_event = mem_cgroup_oom_unregister_event; - } else if (!strcmp(name, "memory.pressure_level")) { - event->register_event = vmpressure_register_event; - event->unregister_event = vmpressure_unregister_event; - } else if (!strcmp(name, "memory.memsw.usage_in_bytes")) { - event->register_event = memsw_cgroup_usage_register_event; - event->unregister_event = memsw_cgroup_usage_unregister_event; - } else { - ret = -EINVAL; - goto out_put_cfile; - } - - /* - * Verify @cfile should belong to @css. Also, remaining events are - * automatically removed on cgroup destruction but the removal is - * asynchronous, so take an extra ref on @css. - */ - cfile_css = css_tryget_online_from_dir(cfile.file->f_path.dentry->d_parent, - &memory_cgrp_subsys); - ret = -EINVAL; - if (IS_ERR(cfile_css)) - goto out_put_cfile; - if (cfile_css != css) { - css_put(cfile_css); - goto out_put_cfile; - } - - ret = event->register_event(memcg, event->eventfd, buf); - if (ret) - goto out_put_css; - - vfs_poll(efile.file, &event->pt); - - spin_lock(&memcg->event_list_lock); - list_add(&event->list, &memcg->event_list); - spin_unlock(&memcg->event_list_lock); - - fdput(cfile); - fdput(efile); - - return nbytes; - -out_put_css: - css_put(css); -out_put_cfile: - fdput(cfile); -out_put_eventfd: - eventfd_ctx_put(event->eventfd); -out_put_efile: - fdput(efile); -out_kfree: - kfree(event); - - return ret; } -static struct cftype mem_cgroup_legacy_files[] = { - { - .name = "usage_in_bytes", - .private = MEMFILE_PRIVATE(_MEM, RES_USAGE), - .read_u64 = mem_cgroup_read_u64, - }, - { - .name = "max_usage_in_bytes", - .private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE), - .write = mem_cgroup_reset, - .read_u64 = mem_cgroup_read_u64, - }, - { - .name = "limit_in_bytes", - .private = MEMFILE_PRIVATE(_MEM, RES_LIMIT), - .write = mem_cgroup_write, - .read_u64 = mem_cgroup_read_u64, - }, - { - .name = "soft_limit_in_bytes", - .private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT), - .write = mem_cgroup_write, - .read_u64 = mem_cgroup_read_u64, - }, - { - .name = "failcnt", - .private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT), - .write = mem_cgroup_reset, - .read_u64 = mem_cgroup_read_u64, - }, - { - .name = "stat", - .seq_show = memcg_stat_show, - }, - { - .name = "force_empty", - .write = mem_cgroup_force_empty_write, - }, - { - .name = "use_hierarchy", - .write_u64 = mem_cgroup_hierarchy_write, - .read_u64 = mem_cgroup_hierarchy_read, - }, - { - .name = "cgroup.event_control", /* XXX: for compat */ - .write = memcg_write_event_control, - .flags = CFTYPE_NO_PREFIX | CFTYPE_WORLD_WRITABLE, - }, - { - .name = "swappiness", - .read_u64 = mem_cgroup_swappiness_read, - .write_u64 = mem_cgroup_swappiness_write, - }, - { - .name = "move_charge_at_immigrate", - .read_u64 = mem_cgroup_move_charge_read, - .write_u64 = mem_cgroup_move_charge_write, - }, - { - .name = "oom_control", - .seq_show = mem_cgroup_oom_control_read, - .write_u64 = mem_cgroup_oom_control_write, - .private = MEMFILE_PRIVATE(_OOM_TYPE, OOM_CONTROL), - }, - { - .name = "pressure_level", - }, -#ifdef CONFIG_NUMA - { - .name = "numa_stat", - .seq_show = memcg_numa_stat_show, - }, -#endif - { - .name = "kmem.limit_in_bytes", - .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT), - .write = mem_cgroup_write, - .read_u64 = mem_cgroup_read_u64, - }, - { - .name = "kmem.usage_in_bytes", - .private = MEMFILE_PRIVATE(_KMEM, RES_USAGE), - .read_u64 = mem_cgroup_read_u64, - }, - { - .name = "kmem.failcnt", - .private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT), - .write = mem_cgroup_reset, - .read_u64 = mem_cgroup_read_u64, - }, - { - .name = "kmem.max_usage_in_bytes", - .private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE), - .write = mem_cgroup_reset, - .read_u64 = mem_cgroup_read_u64, - }, -#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG) - { - .name = "kmem.slabinfo", - .seq_start = memcg_slab_start, - .seq_next = memcg_slab_next, - .seq_stop = memcg_slab_stop, - .seq_show = memcg_slab_show, - }, -#endif - { - .name = "kmem.tcp.limit_in_bytes", - .private = MEMFILE_PRIVATE(_TCP, RES_LIMIT), - .write = mem_cgroup_write, - .read_u64 = mem_cgroup_read_u64, - }, - { - .name = "kmem.tcp.usage_in_bytes", - .private = MEMFILE_PRIVATE(_TCP, RES_USAGE), - .read_u64 = mem_cgroup_read_u64, - }, - { - .name = "kmem.tcp.failcnt", - .private = MEMFILE_PRIVATE(_TCP, RES_FAILCNT), - .write = mem_cgroup_reset, - .read_u64 = mem_cgroup_read_u64, - }, - { - .name = "kmem.tcp.max_usage_in_bytes", - .private = MEMFILE_PRIVATE(_TCP, RES_MAX_USAGE), - .write = mem_cgroup_reset, - .read_u64 = mem_cgroup_read_u64, - }, - { }, /* terminate */ -}; +#endif /* CONFIG_CGROUP_WRITEBACK */ /* * Private memory cgroup IDR @@ -4294,7 +3564,7 @@ static struct cftype mem_cgroup_legacy_files[] = { * limited to 16 bit (MEM_CGROUP_ID_MAX), limiting the total number of * memory-controlled cgroups to 64k. * - * However, there usually are many references to the oflline CSS after + * However, there usually are many references to the offline CSS after * the cgroup has been destroyed, such as page cache or reclaimable * slab objects, that don't need to hang on to the ID. We want to keep * those dead CSS from occupying IDs, or we might quickly exhaust the @@ -4310,17 +3580,19 @@ static struct cftype mem_cgroup_legacy_files[] = { * those references are manageable from userspace. */ -static DEFINE_IDR(mem_cgroup_idr); +#define MEM_CGROUP_ID_MAX ((1UL << MEM_CGROUP_ID_SHIFT) - 1) +static DEFINE_XARRAY_ALLOC1(mem_cgroup_ids); static void mem_cgroup_id_remove(struct mem_cgroup *memcg) { if (memcg->id.id > 0) { - idr_remove(&mem_cgroup_idr, memcg->id.id); + xa_erase(&mem_cgroup_ids, memcg->id.id); memcg->id.id = 0; } } -static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n) +void __maybe_unused mem_cgroup_id_get_many(struct mem_cgroup *memcg, + unsigned int n) { refcount_add(n, &memcg->id.ref); } @@ -4335,14 +3607,27 @@ static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) } } -static inline void mem_cgroup_id_get(struct mem_cgroup *memcg) +static inline void mem_cgroup_id_put(struct mem_cgroup *memcg) { - mem_cgroup_id_get_many(memcg, 1); + mem_cgroup_id_put_many(memcg, 1); } -static inline void mem_cgroup_id_put(struct mem_cgroup *memcg) +struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) { - mem_cgroup_id_put_many(memcg, 1); + while (!refcount_inc_not_zero(&memcg->id.ref)) { + /* + * The root cgroup cannot be destroyed, so it's refcount must + * always be >= 1. + */ + if (WARN_ON_ONCE(mem_cgroup_is_root(memcg))) { + VM_BUG_ON(1); + break; + } + memcg = parent_mem_cgroup(memcg); + if (!memcg) + memcg = root_mem_cgroup; + } + return memcg; } /** @@ -4354,223 +3639,283 @@ static inline void mem_cgroup_id_put(struct mem_cgroup *memcg) struct mem_cgroup *mem_cgroup_from_id(unsigned short id) { WARN_ON_ONCE(!rcu_read_lock_held()); - return idr_find(&mem_cgroup_idr, id); + return xa_load(&mem_cgroup_ids, id); } -static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) +#ifdef CONFIG_SHRINKER_DEBUG +struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino) { - struct mem_cgroup_per_node *pn; - int tmp = node; - /* - * This routine is called against possible nodes. - * But it's BUG to call kmalloc() against offline node. - * - * TODO: this routine can waste much memory for nodes which will - * never be onlined. It's better to use memory hotplug callback - * function. - */ - if (!node_state(node, N_NORMAL_MEMORY)) - tmp = -1; - pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, tmp); - if (!pn) - return 1; + struct cgroup *cgrp; + struct cgroup_subsys_state *css; + struct mem_cgroup *memcg; - pn->lruvec_stat_cpu = alloc_percpu(struct lruvec_stat); - if (!pn->lruvec_stat_cpu) { - kfree(pn); - return 1; - } + cgrp = cgroup_get_from_id(ino); + if (IS_ERR(cgrp)) + return ERR_CAST(cgrp); - lruvec_init(&pn->lruvec); - pn->usage_in_excess = 0; - pn->on_tree = false; - pn->memcg = memcg; + css = cgroup_get_e_css(cgrp, &memory_cgrp_subsys); + if (css) + memcg = container_of(css, struct mem_cgroup, css); + else + memcg = ERR_PTR(-ENOENT); - memcg->nodeinfo[node] = pn; - return 0; + cgroup_put(cgrp); + + return memcg; } +#endif -static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) +static void free_mem_cgroup_per_node_info(struct mem_cgroup_per_node *pn) { - struct mem_cgroup_per_node *pn = memcg->nodeinfo[node]; - if (!pn) return; - free_percpu(pn->lruvec_stat_cpu); + free_percpu(pn->lruvec_stats_percpu); + kfree(pn->lruvec_stats); kfree(pn); } +static bool alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) +{ + struct mem_cgroup_per_node *pn; + + pn = kmem_cache_alloc_node(memcg_pn_cachep, GFP_KERNEL | __GFP_ZERO, + node); + if (!pn) + return false; + + pn->lruvec_stats = kzalloc_node(sizeof(struct lruvec_stats), + GFP_KERNEL_ACCOUNT, node); + if (!pn->lruvec_stats) + goto fail; + + pn->lruvec_stats_percpu = alloc_percpu_gfp(struct lruvec_stats_percpu, + GFP_KERNEL_ACCOUNT); + if (!pn->lruvec_stats_percpu) + goto fail; + + lruvec_init(&pn->lruvec); + pn->memcg = memcg; + + memcg->nodeinfo[node] = pn; + return true; +fail: + free_mem_cgroup_per_node_info(pn); + return false; +} + static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; + obj_cgroup_put(memcg->orig_objcg); + for_each_node(node) - free_mem_cgroup_per_node_info(memcg, node); - free_percpu(memcg->stat_cpu); + free_mem_cgroup_per_node_info(memcg->nodeinfo[node]); + memcg1_free_events(memcg); + kfree(memcg->vmstats); + free_percpu(memcg->vmstats_percpu); kfree(memcg); } static void mem_cgroup_free(struct mem_cgroup *memcg) { + lru_gen_exit_memcg(memcg); memcg_wb_domain_exit(memcg); __mem_cgroup_free(memcg); } -static struct mem_cgroup *mem_cgroup_alloc(void) +static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent) { + struct memcg_vmstats_percpu *statc; + struct memcg_vmstats_percpu __percpu *pstatc_pcpu; struct mem_cgroup *memcg; - size_t size; - int node; - - size = sizeof(struct mem_cgroup); - size += nr_node_ids * sizeof(struct mem_cgroup_per_node *); + int node, cpu; + int __maybe_unused i; + long error; - memcg = kzalloc(size, GFP_KERNEL); + memcg = kmem_cache_zalloc(memcg_cachep, GFP_KERNEL); if (!memcg) - return NULL; + return ERR_PTR(-ENOMEM); - memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, - 1, MEM_CGROUP_ID_MAX, - GFP_KERNEL); - if (memcg->id.id < 0) + error = xa_alloc(&mem_cgroup_ids, &memcg->id.id, NULL, + XA_LIMIT(1, MEM_CGROUP_ID_MAX), GFP_KERNEL); + if (error) goto fail; + error = -ENOMEM; - memcg->stat_cpu = alloc_percpu(struct mem_cgroup_stat_cpu); - if (!memcg->stat_cpu) + memcg->vmstats = kzalloc(sizeof(struct memcg_vmstats), + GFP_KERNEL_ACCOUNT); + if (!memcg->vmstats) goto fail; + memcg->vmstats_percpu = alloc_percpu_gfp(struct memcg_vmstats_percpu, + GFP_KERNEL_ACCOUNT); + if (!memcg->vmstats_percpu) + goto fail; + + if (!memcg1_alloc_events(memcg)) + goto fail; + + for_each_possible_cpu(cpu) { + if (parent) + pstatc_pcpu = parent->vmstats_percpu; + statc = per_cpu_ptr(memcg->vmstats_percpu, cpu); + statc->parent_pcpu = parent ? pstatc_pcpu : NULL; + statc->vmstats = memcg->vmstats; + } + for_each_node(node) - if (alloc_mem_cgroup_per_node_info(memcg, node)) + if (!alloc_mem_cgroup_per_node_info(memcg, node)) goto fail; if (memcg_wb_domain_init(memcg, GFP_KERNEL)) goto fail; INIT_WORK(&memcg->high_work, high_work_func); - memcg->last_scanned_node = MAX_NUMNODES; - INIT_LIST_HEAD(&memcg->oom_notify); - mutex_init(&memcg->thresholds_lock); - spin_lock_init(&memcg->move_lock); vmpressure_init(&memcg->vmpressure); - INIT_LIST_HEAD(&memcg->event_list); - spin_lock_init(&memcg->event_list_lock); - memcg->socket_pressure = jiffies; -#ifdef CONFIG_MEMCG_KMEM - memcg->kmemcg_id = -1; + INIT_LIST_HEAD(&memcg->memory_peaks); + INIT_LIST_HEAD(&memcg->swap_peaks); + spin_lock_init(&memcg->peaks_lock); + memcg->socket_pressure = get_jiffies_64(); +#if BITS_PER_LONG < 64 + seqlock_init(&memcg->socket_pressure_seqlock); #endif + memcg1_memcg_init(memcg); + memcg->kmemcg_id = -1; + INIT_LIST_HEAD(&memcg->objcg_list); #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&memcg->cgwb_list); + for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) + memcg->cgwb_frn[i].done = + __WB_COMPLETION_INIT(&memcg_cgwb_frn_waitq); #endif - idr_replace(&mem_cgroup_idr, memcg, memcg->id.id); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + spin_lock_init(&memcg->deferred_split_queue.split_queue_lock); + INIT_LIST_HEAD(&memcg->deferred_split_queue.split_queue); + memcg->deferred_split_queue.split_queue_len = 0; +#endif + lru_gen_init_memcg(memcg); return memcg; fail: mem_cgroup_id_remove(memcg); __mem_cgroup_free(memcg); - return NULL; + return ERR_PTR(error); } static struct cgroup_subsys_state * __ref mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { struct mem_cgroup *parent = mem_cgroup_from_css(parent_css); - struct mem_cgroup *memcg; - long error = -ENOMEM; - - memcg = mem_cgroup_alloc(); - if (!memcg) - return ERR_PTR(error); - - memcg->high = PAGE_COUNTER_MAX; - memcg->soft_limit = PAGE_COUNTER_MAX; + struct mem_cgroup *memcg, *old_memcg; + bool memcg_on_dfl = cgroup_subsys_on_dfl(memory_cgrp_subsys); + + old_memcg = set_active_memcg(parent); + memcg = mem_cgroup_alloc(parent); + set_active_memcg(old_memcg); + if (IS_ERR(memcg)) + return ERR_CAST(memcg); + + page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX); + memcg1_soft_limit_reset(memcg); +#ifdef CONFIG_ZSWAP + memcg->zswap_max = PAGE_COUNTER_MAX; + WRITE_ONCE(memcg->zswap_writeback, true); +#endif + page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX); if (parent) { - memcg->swappiness = mem_cgroup_swappiness(parent); - memcg->oom_kill_disable = parent->oom_kill_disable; - } - if (parent && parent->use_hierarchy) { - memcg->use_hierarchy = true; - page_counter_init(&memcg->memory, &parent->memory); - page_counter_init(&memcg->swap, &parent->swap); - page_counter_init(&memcg->memsw, &parent->memsw); - page_counter_init(&memcg->kmem, &parent->kmem); - page_counter_init(&memcg->tcpmem, &parent->tcpmem); + WRITE_ONCE(memcg->swappiness, mem_cgroup_swappiness(parent)); + + page_counter_init(&memcg->memory, &parent->memory, memcg_on_dfl); + page_counter_init(&memcg->swap, &parent->swap, false); +#ifdef CONFIG_MEMCG_V1 + memcg->memory.track_failcnt = !memcg_on_dfl; + WRITE_ONCE(memcg->oom_kill_disable, READ_ONCE(parent->oom_kill_disable)); + page_counter_init(&memcg->kmem, &parent->kmem, false); + page_counter_init(&memcg->tcpmem, &parent->tcpmem, false); +#endif } else { - page_counter_init(&memcg->memory, NULL); - page_counter_init(&memcg->swap, NULL); - page_counter_init(&memcg->memsw, NULL); - page_counter_init(&memcg->kmem, NULL); - page_counter_init(&memcg->tcpmem, NULL); - /* - * Deeper hierachy with use_hierarchy == false doesn't make - * much sense so let cgroup subsystem know about this - * unfortunate state in our controller. - */ - if (parent != root_mem_cgroup) - memory_cgrp_subsys.broken_hierarchy = true; - } - - /* The following stuff does not apply to the root */ - if (!parent) { + init_memcg_stats(); + init_memcg_events(); + page_counter_init(&memcg->memory, NULL, true); + page_counter_init(&memcg->swap, NULL, false); +#ifdef CONFIG_MEMCG_V1 + page_counter_init(&memcg->kmem, NULL, false); + page_counter_init(&memcg->tcpmem, NULL, false); +#endif root_mem_cgroup = memcg; return &memcg->css; } - error = memcg_online_kmem(memcg); - if (error) - goto fail; - - if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket) + if (memcg_on_dfl && !cgroup_memory_nosocket) static_branch_inc(&memcg_sockets_enabled_key); + if (!cgroup_memory_nobpf) + static_branch_inc(&memcg_bpf_enabled_key); + return &memcg->css; -fail: - mem_cgroup_id_remove(memcg); - mem_cgroup_free(memcg); - return ERR_PTR(-ENOMEM); } static int mem_cgroup_css_online(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); + if (memcg_online_kmem(memcg)) + goto remove_id; + /* - * A memcg must be visible for memcg_expand_shrinker_maps() + * A memcg must be visible for expand_shrinker_info() * by the time the maps are allocated. So, we allocate maps * here, when for_each_mem_cgroup() can't skip it. */ - if (memcg_alloc_shrinker_maps(memcg)) { - mem_cgroup_id_remove(memcg); - return -ENOMEM; - } + if (alloc_shrinker_info(memcg)) + goto offline_kmem; + + if (unlikely(mem_cgroup_is_root(memcg)) && !mem_cgroup_disabled()) + queue_delayed_work(system_unbound_wq, &stats_flush_dwork, + FLUSH_TIME); + lru_gen_online_memcg(memcg); /* Online state pins memcg ID, memcg ID pins CSS */ refcount_set(&memcg->id.ref, 1); css_get(css); + + /* + * Ensure mem_cgroup_from_id() works once we're fully online. + * + * We could do this earlier and require callers to filter with + * css_tryget_online(). But right now there are no users that + * need earlier access, and the workingset code relies on the + * cgroup tree linkage (mem_cgroup_get_nr_swap_pages()). So + * publish it here at the end of onlining. This matches the + * regular ID destruction during offlining. + */ + xa_store(&mem_cgroup_ids, memcg->id.id, memcg, GFP_KERNEL); + return 0; +offline_kmem: + memcg_offline_kmem(memcg); +remove_id: + mem_cgroup_id_remove(memcg); + return -ENOMEM; } static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct mem_cgroup_event *event, *tmp; - /* - * Unregister events and notify userspace. - * Notify userspace about cgroup removing only after rmdir of cgroup - * directory to avoid race between userspace and kernelspace. - */ - spin_lock(&memcg->event_list_lock); - list_for_each_entry_safe(event, tmp, &memcg->event_list, list) { - list_del_init(&event->list); - schedule_work(&event->remove); - } - spin_unlock(&memcg->event_list_lock); + memcg1_css_offline(memcg); page_counter_set_min(&memcg->memory, 0); page_counter_set_low(&memcg->memory, 0); + zswap_memcg_offline_cleanup(memcg); + memcg_offline_kmem(memcg); + reparent_deferred_split_queue(memcg); + reparent_shrinker_deferred(memcg); wb_memcg_offline(memcg); + lru_gen_offline_memcg(memcg); drain_all_stock(memcg); @@ -4582,23 +3927,31 @@ static void mem_cgroup_css_released(struct cgroup_subsys_state *css) struct mem_cgroup *memcg = mem_cgroup_from_css(css); invalidate_reclaim_iterators(memcg); + lru_gen_release_memcg(memcg); } static void mem_cgroup_css_free(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); + int __maybe_unused i; +#ifdef CONFIG_CGROUP_WRITEBACK + for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) + wb_wait_for_completion(&memcg->cgwb_frn[i].done); +#endif if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket) static_branch_dec(&memcg_sockets_enabled_key); - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_active) + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg1_tcpmem_active(memcg)) static_branch_dec(&memcg_sockets_enabled_key); + if (!cgroup_memory_nobpf) + static_branch_dec(&memcg_bpf_enabled_key); + vmpressure_cleanup(&memcg->vmpressure); cancel_work_sync(&memcg->high_work); - mem_cgroup_remove_from_trees(memcg); - memcg_free_shrinker_maps(memcg); - memcg_free_kmem(memcg); + memcg1_remove_from_trees(memcg); + free_shrinker_info(memcg); mem_cgroup_free(memcg); } @@ -4621,758 +3974,355 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) page_counter_set_max(&memcg->memory, PAGE_COUNTER_MAX); page_counter_set_max(&memcg->swap, PAGE_COUNTER_MAX); - page_counter_set_max(&memcg->memsw, PAGE_COUNTER_MAX); +#ifdef CONFIG_MEMCG_V1 page_counter_set_max(&memcg->kmem, PAGE_COUNTER_MAX); page_counter_set_max(&memcg->tcpmem, PAGE_COUNTER_MAX); +#endif page_counter_set_min(&memcg->memory, 0); page_counter_set_low(&memcg->memory, 0); - memcg->high = PAGE_COUNTER_MAX; - memcg->soft_limit = PAGE_COUNTER_MAX; + page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX); + memcg1_soft_limit_reset(memcg); + page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX); memcg_wb_domain_size_changed(memcg); } -#ifdef CONFIG_MMU -/* Handlers for move charge at task migration. */ -static int mem_cgroup_do_precharge(unsigned long count) -{ - int ret; - - /* Try a single bulk charge without reclaim first, kswapd may wake */ - ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_DIRECT_RECLAIM, count); - if (!ret) { - mc.precharge += count; - return ret; - } - - /* Try charges one by one with reclaim, but do not retry */ - while (count--) { - ret = try_charge(mc.to, GFP_KERNEL | __GFP_NORETRY, 1); - if (ret) - return ret; - mc.precharge++; - cond_resched(); - } - return 0; -} - -union mc_target { - struct page *page; - swp_entry_t ent; +struct aggregate_control { + /* pointer to the aggregated (CPU and subtree aggregated) counters */ + long *aggregate; + /* pointer to the non-hierarchichal (CPU aggregated) counters */ + long *local; + /* pointer to the pending child counters during tree propagation */ + long *pending; + /* pointer to the parent's pending counters, could be NULL */ + long *ppending; + /* pointer to the percpu counters to be aggregated */ + long *cstat; + /* pointer to the percpu counters of the last aggregation*/ + long *cstat_prev; + /* size of the above counters */ + int size; }; -enum mc_target_type { - MC_TARGET_NONE = 0, - MC_TARGET_PAGE, - MC_TARGET_SWAP, - MC_TARGET_DEVICE, -}; - -static struct page *mc_handle_present_pte(struct vm_area_struct *vma, - unsigned long addr, pte_t ptent) +static void mem_cgroup_stat_aggregate(struct aggregate_control *ac) { - struct page *page = _vm_normal_page(vma, addr, ptent, true); + int i; + long delta, delta_cpu, v; - if (!page || !page_mapped(page)) - return NULL; - if (PageAnon(page)) { - if (!(mc.flags & MOVE_ANON)) - return NULL; - } else { - if (!(mc.flags & MOVE_FILE)) - return NULL; - } - if (!get_page_unless_zero(page)) - return NULL; + for (i = 0; i < ac->size; i++) { + /* + * Collect the aggregated propagation counts of groups + * below us. We're in a per-cpu loop here and this is + * a global counter, so the first cycle will get them. + */ + delta = ac->pending[i]; + if (delta) + ac->pending[i] = 0; + + /* Add CPU changes on this level since the last flush */ + delta_cpu = 0; + v = READ_ONCE(ac->cstat[i]); + if (v != ac->cstat_prev[i]) { + delta_cpu = v - ac->cstat_prev[i]; + delta += delta_cpu; + ac->cstat_prev[i] = v; + } + + /* Aggregate counts on this level and propagate upwards */ + if (delta_cpu) + ac->local[i] += delta_cpu; - return page; + if (delta) { + ac->aggregate[i] += delta; + if (ac->ppending) + ac->ppending[i] += delta; + } + } } -#if defined(CONFIG_SWAP) || defined(CONFIG_DEVICE_PRIVATE) -static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, - pte_t ptent, swp_entry_t *entry) +#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC +static void flush_nmi_stats(struct mem_cgroup *memcg, struct mem_cgroup *parent, + int cpu) { - struct page *page = NULL; - swp_entry_t ent = pte_to_swp_entry(ptent); + int nid; - if (!(mc.flags & MOVE_ANON) || non_swap_entry(ent)) - return NULL; + if (atomic_read(&memcg->kmem_stat)) { + int kmem = atomic_xchg(&memcg->kmem_stat, 0); + int index = memcg_stats_index(MEMCG_KMEM); - /* - * Handle MEMORY_DEVICE_PRIVATE which are ZONE_DEVICE page belonging to - * a device and because they are not accessible by CPU they are store - * as special swap entry in the CPU page table. - */ - if (is_device_private_entry(ent)) { - page = device_private_entry_to_page(ent); - /* - * MEMORY_DEVICE_PRIVATE means ZONE_DEVICE page and which have - * a refcount of 1 when free (unlike normal page) - */ - if (!page_ref_add_unless(page, 1, 1)) - return NULL; - return page; + memcg->vmstats->state[index] += kmem; + if (parent) + parent->vmstats->state_pending[index] += kmem; } - /* - * Because lookup_swap_cache() updates some statistics counter, - * we call find_get_page() with swapper_space directly. - */ - page = find_get_page(swap_address_space(ent), swp_offset(ent)); - if (do_memsw_account()) - entry->val = ent.val; + for_each_node_state(nid, N_MEMORY) { + struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid]; + struct lruvec_stats *lstats = pn->lruvec_stats; + struct lruvec_stats *plstats = NULL; - return page; -} -#else -static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, - pte_t ptent, swp_entry_t *entry) -{ - return NULL; -} -#endif + if (parent) + plstats = parent->nodeinfo[nid]->lruvec_stats; -static struct page *mc_handle_file_pte(struct vm_area_struct *vma, - unsigned long addr, pte_t ptent, swp_entry_t *entry) -{ - struct page *page = NULL; - struct address_space *mapping; - pgoff_t pgoff; + if (atomic_read(&pn->slab_reclaimable)) { + int slab = atomic_xchg(&pn->slab_reclaimable, 0); + int index = memcg_stats_index(NR_SLAB_RECLAIMABLE_B); - if (!vma->vm_file) /* anonymous vma */ - return NULL; - if (!(mc.flags & MOVE_FILE)) - return NULL; - - mapping = vma->vm_file->f_mapping; - pgoff = linear_page_index(vma, addr); + lstats->state[index] += slab; + if (plstats) + plstats->state_pending[index] += slab; + } + if (atomic_read(&pn->slab_unreclaimable)) { + int slab = atomic_xchg(&pn->slab_unreclaimable, 0); + int index = memcg_stats_index(NR_SLAB_UNRECLAIMABLE_B); - /* page is moved even if it's not RSS of this task(page-faulted). */ -#ifdef CONFIG_SWAP - /* shmem/tmpfs may report page out on swap: account for that too. */ - if (shmem_mapping(mapping)) { - page = find_get_entry(mapping, pgoff); - if (xa_is_value(page)) { - swp_entry_t swp = radix_to_swp_entry(page); - if (do_memsw_account()) - *entry = swp; - page = find_get_page(swap_address_space(swp), - swp_offset(swp)); + lstats->state[index] += slab; + if (plstats) + plstats->state_pending[index] += slab; } - } else - page = find_get_page(mapping, pgoff); + } +} #else - page = find_get_page(mapping, pgoff); +static void flush_nmi_stats(struct mem_cgroup *memcg, struct mem_cgroup *parent, + int cpu) +{} #endif - return page; -} -/** - * mem_cgroup_move_account - move account of the page - * @page: the page - * @compound: charge the page as compound or small page - * @from: mem_cgroup which the page is moved from. - * @to: mem_cgroup which the page is moved to. @from != @to. - * - * The caller must make sure the page is not on LRU (isolate_page() is useful.) - * - * This function doesn't do "charge" to new cgroup and doesn't do "uncharge" - * from old cgroup. - */ -static int mem_cgroup_move_account(struct page *page, - bool compound, - struct mem_cgroup *from, - struct mem_cgroup *to) +static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu) { - unsigned long flags; - unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; - int ret; - bool anon; + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *parent = parent_mem_cgroup(memcg); + struct memcg_vmstats_percpu *statc; + struct aggregate_control ac; + int nid; - VM_BUG_ON(from == to); - VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON(compound && !PageTransHuge(page)); + flush_nmi_stats(memcg, parent, cpu); - /* - * Prevent mem_cgroup_migrate() from looking at - * page->mem_cgroup of its source page while we change it. - */ - ret = -EBUSY; - if (!trylock_page(page)) - goto out; - - ret = -EINVAL; - if (page->mem_cgroup != from) - goto out_unlock; + statc = per_cpu_ptr(memcg->vmstats_percpu, cpu); - anon = PageAnon(page); + ac = (struct aggregate_control) { + .aggregate = memcg->vmstats->state, + .local = memcg->vmstats->state_local, + .pending = memcg->vmstats->state_pending, + .ppending = parent ? parent->vmstats->state_pending : NULL, + .cstat = statc->state, + .cstat_prev = statc->state_prev, + .size = MEMCG_VMSTAT_SIZE, + }; + mem_cgroup_stat_aggregate(&ac); + + ac = (struct aggregate_control) { + .aggregate = memcg->vmstats->events, + .local = memcg->vmstats->events_local, + .pending = memcg->vmstats->events_pending, + .ppending = parent ? parent->vmstats->events_pending : NULL, + .cstat = statc->events, + .cstat_prev = statc->events_prev, + .size = NR_MEMCG_EVENTS, + }; + mem_cgroup_stat_aggregate(&ac); - spin_lock_irqsave(&from->move_lock, flags); + for_each_node_state(nid, N_MEMORY) { + struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid]; + struct lruvec_stats *lstats = pn->lruvec_stats; + struct lruvec_stats *plstats = NULL; + struct lruvec_stats_percpu *lstatc; - if (!anon && page_mapped(page)) { - __mod_memcg_state(from, NR_FILE_MAPPED, -nr_pages); - __mod_memcg_state(to, NR_FILE_MAPPED, nr_pages); - } + if (parent) + plstats = parent->nodeinfo[nid]->lruvec_stats; - /* - * move_lock grabbed above and caller set from->moving_account, so - * mod_memcg_page_state will serialize updates to PageDirty. - * So mapping should be stable for dirty pages. - */ - if (!anon && PageDirty(page)) { - struct address_space *mapping = page_mapping(page); + lstatc = per_cpu_ptr(pn->lruvec_stats_percpu, cpu); - if (mapping_cap_account_dirty(mapping)) { - __mod_memcg_state(from, NR_FILE_DIRTY, -nr_pages); - __mod_memcg_state(to, NR_FILE_DIRTY, nr_pages); - } - } + ac = (struct aggregate_control) { + .aggregate = lstats->state, + .local = lstats->state_local, + .pending = lstats->state_pending, + .ppending = plstats ? plstats->state_pending : NULL, + .cstat = lstatc->state, + .cstat_prev = lstatc->state_prev, + .size = NR_MEMCG_NODE_STAT_ITEMS, + }; + mem_cgroup_stat_aggregate(&ac); - if (PageWriteback(page)) { - __mod_memcg_state(from, NR_WRITEBACK, -nr_pages); - __mod_memcg_state(to, NR_WRITEBACK, nr_pages); } + WRITE_ONCE(statc->stats_updates, 0); + /* We are in a per-cpu loop here, only do the atomic write once */ + if (atomic_read(&memcg->vmstats->stats_updates)) + atomic_set(&memcg->vmstats->stats_updates, 0); +} +static void mem_cgroup_fork(struct task_struct *task) +{ /* - * It is safe to change page->mem_cgroup here because the page - * is referenced, charged, and isolated - we can't race with - * uncharging, charging, migration, or LRU putback. + * Set the update flag to cause task->objcg to be initialized lazily + * on the first allocation. It can be done without any synchronization + * because it's always performed on the current task, so does + * current_objcg_update(). */ - - /* caller should have done css_get */ - page->mem_cgroup = to; - spin_unlock_irqrestore(&from->move_lock, flags); - - ret = 0; - - local_irq_disable(); - mem_cgroup_charge_statistics(to, page, compound, nr_pages); - memcg_check_events(to, page); - mem_cgroup_charge_statistics(from, page, compound, -nr_pages); - memcg_check_events(from, page); - local_irq_enable(); -out_unlock: - unlock_page(page); -out: - return ret; + task->objcg = (struct obj_cgroup *)CURRENT_OBJCG_UPDATE_FLAG; } -/** - * get_mctgt_type - get target type of moving charge - * @vma: the vma the pte to be checked belongs - * @addr: the address corresponding to the pte to be checked - * @ptent: the pte to be checked - * @target: the pointer the target page or swap ent will be stored(can be NULL) - * - * Returns - * 0(MC_TARGET_NONE): if the pte is not a target for move charge. - * 1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for - * move charge. if @target is not NULL, the page is stored in target->page - * with extra refcnt got(Callers should handle it). - * 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a - * target for charge migration. if @target is not NULL, the entry is stored - * in target->ent. - * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is MEMORY_DEVICE_PUBLIC - * or MEMORY_DEVICE_PRIVATE (so ZONE_DEVICE page and thus not on the lru). - * For now we such page is charge like a regular page would be as for all - * intent and purposes it is just special memory taking the place of a - * regular page. - * - * See Documentations/vm/hmm.txt and include/linux/hmm.h - * - * Called with pte lock held. - */ - -static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, - unsigned long addr, pte_t ptent, union mc_target *target) +static void mem_cgroup_exit(struct task_struct *task) { - struct page *page = NULL; - enum mc_target_type ret = MC_TARGET_NONE; - swp_entry_t ent = { .val = 0 }; + struct obj_cgroup *objcg = task->objcg; - if (pte_present(ptent)) - page = mc_handle_present_pte(vma, addr, ptent); - else if (is_swap_pte(ptent)) - page = mc_handle_swap_pte(vma, ptent, &ent); - else if (pte_none(ptent)) - page = mc_handle_file_pte(vma, addr, ptent, &ent); + objcg = (struct obj_cgroup *) + ((unsigned long)objcg & ~CURRENT_OBJCG_UPDATE_FLAG); + obj_cgroup_put(objcg); - if (!page && !ent.val) - return ret; - if (page) { - /* - * Do only loose check w/o serialization. - * mem_cgroup_move_account() checks the page is valid or - * not under LRU exclusion. - */ - if (page->mem_cgroup == mc.from) { - ret = MC_TARGET_PAGE; - if (is_device_private_page(page) || - is_device_public_page(page)) - ret = MC_TARGET_DEVICE; - if (target) - target->page = page; - } - if (!ret || !target) - put_page(page); - } /* - * There is a swap entry and a page doesn't exist or isn't charged. - * But we cannot move a tail-page in a THP. + * Some kernel allocations can happen after this point, + * but let's ignore them. It can be done without any synchronization + * because it's always performed on the current task, so does + * current_objcg_update(). */ - if (ent.val && !ret && (!page || !PageTransCompound(page)) && - mem_cgroup_id(mc.from) == lookup_swap_cgroup_id(ent)) { - ret = MC_TARGET_SWAP; - if (target) - target->ent = ent; - } - return ret; + task->objcg = NULL; } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -/* - * We don't consider PMD mapped swapping or file mapped pages because THP does - * not support them for now. - * Caller should make sure that pmd_trans_huge(pmd) is true. - */ -static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma, - unsigned long addr, pmd_t pmd, union mc_target *target) +#ifdef CONFIG_LRU_GEN +static void mem_cgroup_lru_gen_attach(struct cgroup_taskset *tset) { - struct page *page = NULL; - enum mc_target_type ret = MC_TARGET_NONE; + struct task_struct *task; + struct cgroup_subsys_state *css; - if (unlikely(is_swap_pmd(pmd))) { - VM_BUG_ON(thp_migration_supported() && - !is_pmd_migration_entry(pmd)); - return ret; - } - page = pmd_page(pmd); - VM_BUG_ON_PAGE(!page || !PageHead(page), page); - if (!(mc.flags & MOVE_ANON)) - return ret; - if (page->mem_cgroup == mc.from) { - ret = MC_TARGET_PAGE; - if (target) { - get_page(page); - target->page = page; - } - } - return ret; + /* find the first leader if there is any */ + cgroup_taskset_for_each_leader(task, css, tset) + break; + + if (!task) + return; + + task_lock(task); + if (task->mm && READ_ONCE(task->mm->owner) == task) + lru_gen_migrate_mm(task->mm); + task_unlock(task); } #else -static inline enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma, - unsigned long addr, pmd_t pmd, union mc_target *target) -{ - return MC_TARGET_NONE; -} -#endif +static void mem_cgroup_lru_gen_attach(struct cgroup_taskset *tset) {} +#endif /* CONFIG_LRU_GEN */ -static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, - unsigned long addr, unsigned long end, - struct mm_walk *walk) +static void mem_cgroup_kmem_attach(struct cgroup_taskset *tset) { - struct vm_area_struct *vma = walk->vma; - pte_t *pte; - spinlock_t *ptl; + struct task_struct *task; + struct cgroup_subsys_state *css; - ptl = pmd_trans_huge_lock(pmd, vma); - if (ptl) { - /* - * Note their can not be MC_TARGET_DEVICE for now as we do not - * support transparent huge page with MEMORY_DEVICE_PUBLIC or - * MEMORY_DEVICE_PRIVATE but this might change. - */ - if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE) - mc.precharge += HPAGE_PMD_NR; - spin_unlock(ptl); - return 0; + cgroup_taskset_for_each(task, css, tset) { + /* atomically set the update bit */ + set_bit(CURRENT_OBJCG_UPDATE_BIT, (unsigned long *)&task->objcg); } - - if (pmd_trans_unstable(pmd)) - return 0; - pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); - for (; addr != end; pte++, addr += PAGE_SIZE) - if (get_mctgt_type(vma, addr, *pte, NULL)) - mc.precharge++; /* increment precharge temporarily */ - pte_unmap_unlock(pte - 1, ptl); - cond_resched(); - - return 0; } -static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm) +static void mem_cgroup_attach(struct cgroup_taskset *tset) { - unsigned long precharge; - - struct mm_walk mem_cgroup_count_precharge_walk = { - .pmd_entry = mem_cgroup_count_precharge_pte_range, - .mm = mm, - }; - down_read(&mm->mmap_sem); - walk_page_range(0, mm->highest_vm_end, - &mem_cgroup_count_precharge_walk); - up_read(&mm->mmap_sem); - - precharge = mc.precharge; - mc.precharge = 0; - - return precharge; + mem_cgroup_lru_gen_attach(tset); + mem_cgroup_kmem_attach(tset); } -static int mem_cgroup_precharge_mc(struct mm_struct *mm) +static int seq_puts_memcg_tunable(struct seq_file *m, unsigned long value) { - unsigned long precharge = mem_cgroup_count_precharge(mm); + if (value == PAGE_COUNTER_MAX) + seq_puts(m, "max\n"); + else + seq_printf(m, "%llu\n", (u64)value * PAGE_SIZE); - VM_BUG_ON(mc.moving_task); - mc.moving_task = current; - return mem_cgroup_do_precharge(precharge); + return 0; } -/* cancels all extra charges on mc.from and mc.to, and wakes up all waiters. */ -static void __mem_cgroup_clear_mc(void) +static u64 memory_current_read(struct cgroup_subsys_state *css, + struct cftype *cft) { - struct mem_cgroup *from = mc.from; - struct mem_cgroup *to = mc.to; + struct mem_cgroup *memcg = mem_cgroup_from_css(css); - /* we must uncharge all the leftover precharges from mc.to */ - if (mc.precharge) { - cancel_charge(mc.to, mc.precharge); - mc.precharge = 0; - } - /* - * we didn't uncharge from mc.from at mem_cgroup_move_account(), so - * we must uncharge here. - */ - if (mc.moved_charge) { - cancel_charge(mc.from, mc.moved_charge); - mc.moved_charge = 0; - } - /* we must fixup refcnts and charges */ - if (mc.moved_swap) { - /* uncharge swap account from the old cgroup */ - if (!mem_cgroup_is_root(mc.from)) - page_counter_uncharge(&mc.from->memsw, mc.moved_swap); + return (u64)page_counter_read(&memcg->memory) * PAGE_SIZE; +} - mem_cgroup_id_put_many(mc.from, mc.moved_swap); +#define OFP_PEAK_UNSET (((-1UL))) - /* - * we charged both to->memory and to->memsw, so we - * should uncharge to->memory. - */ - if (!mem_cgroup_is_root(mc.to)) - page_counter_uncharge(&mc.to->memory, mc.moved_swap); +static int peak_show(struct seq_file *sf, void *v, struct page_counter *pc) +{ + struct cgroup_of_peak *ofp = of_peak(sf->private); + u64 fd_peak = READ_ONCE(ofp->value), peak; - mem_cgroup_id_get_many(mc.to, mc.moved_swap); - css_put_many(&mc.to->css, mc.moved_swap); + /* User wants global or local peak? */ + if (fd_peak == OFP_PEAK_UNSET) + peak = pc->watermark; + else + peak = max(fd_peak, READ_ONCE(pc->local_watermark)); - mc.moved_swap = 0; - } - memcg_oom_recover(from); - memcg_oom_recover(to); - wake_up_all(&mc.waitq); + seq_printf(sf, "%llu\n", peak * PAGE_SIZE); + return 0; } -static void mem_cgroup_clear_mc(void) +static int memory_peak_show(struct seq_file *sf, void *v) { - struct mm_struct *mm = mc.mm; - - /* - * we must clear moving_task before waking up waiters at the end of - * task migration. - */ - mc.moving_task = NULL; - __mem_cgroup_clear_mc(); - spin_lock(&mc.lock); - mc.from = NULL; - mc.to = NULL; - mc.mm = NULL; - spin_unlock(&mc.lock); + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(sf)); - mmput(mm); + return peak_show(sf, v, &memcg->memory); } -static int mem_cgroup_can_attach(struct cgroup_taskset *tset) +static int peak_open(struct kernfs_open_file *of) { - struct cgroup_subsys_state *css; - struct mem_cgroup *memcg = NULL; /* unneeded init to make gcc happy */ - struct mem_cgroup *from; - struct task_struct *leader, *p; - struct mm_struct *mm; - unsigned long move_flags; - int ret = 0; - - /* charge immigration isn't supported on the default hierarchy */ - if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) - return 0; - - /* - * Multi-process migrations only happen on the default hierarchy - * where charge immigration is not used. Perform charge - * immigration if @tset contains a leader and whine if there are - * multiple. - */ - p = NULL; - cgroup_taskset_for_each_leader(leader, css, tset) { - WARN_ON_ONCE(p); - p = leader; - memcg = mem_cgroup_from_css(css); - } - if (!p) - return 0; - - /* - * We are now commited to this value whatever it is. Changes in this - * tunable will only affect upcoming migrations, not the current one. - * So we need to save it, and keep it going. - */ - move_flags = READ_ONCE(memcg->move_charge_at_immigrate); - if (!move_flags) - return 0; + struct cgroup_of_peak *ofp = of_peak(of); - from = mem_cgroup_from_task(p); - - VM_BUG_ON(from == memcg); - - mm = get_task_mm(p); - if (!mm) - return 0; - /* We move charges only when we move a owner of the mm */ - if (mm->owner == p) { - VM_BUG_ON(mc.from); - VM_BUG_ON(mc.to); - VM_BUG_ON(mc.precharge); - VM_BUG_ON(mc.moved_charge); - VM_BUG_ON(mc.moved_swap); - - spin_lock(&mc.lock); - mc.mm = mm; - mc.from = from; - mc.to = memcg; - mc.flags = move_flags; - spin_unlock(&mc.lock); - /* We set mc.moving_task later */ - - ret = mem_cgroup_precharge_mc(mm); - if (ret) - mem_cgroup_clear_mc(); - } else { - mmput(mm); - } - return ret; + ofp->value = OFP_PEAK_UNSET; + return 0; } -static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) +static void peak_release(struct kernfs_open_file *of) { - if (mc.to) - mem_cgroup_clear_mc(); -} + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + struct cgroup_of_peak *ofp = of_peak(of); -static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, - unsigned long addr, unsigned long end, - struct mm_walk *walk) -{ - int ret = 0; - struct vm_area_struct *vma = walk->vma; - pte_t *pte; - spinlock_t *ptl; - enum mc_target_type target_type; - union mc_target target; - struct page *page; - - ptl = pmd_trans_huge_lock(pmd, vma); - if (ptl) { - if (mc.precharge < HPAGE_PMD_NR) { - spin_unlock(ptl); - return 0; - } - target_type = get_mctgt_type_thp(vma, addr, *pmd, &target); - if (target_type == MC_TARGET_PAGE) { - page = target.page; - if (!isolate_lru_page(page)) { - if (!mem_cgroup_move_account(page, true, - mc.from, mc.to)) { - mc.precharge -= HPAGE_PMD_NR; - mc.moved_charge += HPAGE_PMD_NR; - } - putback_lru_page(page); - } - put_page(page); - } else if (target_type == MC_TARGET_DEVICE) { - page = target.page; - if (!mem_cgroup_move_account(page, true, - mc.from, mc.to)) { - mc.precharge -= HPAGE_PMD_NR; - mc.moved_charge += HPAGE_PMD_NR; - } - put_page(page); - } - spin_unlock(ptl); - return 0; + if (ofp->value == OFP_PEAK_UNSET) { + /* fast path (no writes on this fd) */ + return; } + spin_lock(&memcg->peaks_lock); + list_del(&ofp->list); + spin_unlock(&memcg->peaks_lock); +} - if (pmd_trans_unstable(pmd)) - return 0; -retry: - pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); - for (; addr != end; addr += PAGE_SIZE) { - pte_t ptent = *(pte++); - bool device = false; - swp_entry_t ent; - - if (!mc.precharge) - break; +static ssize_t peak_write(struct kernfs_open_file *of, char *buf, size_t nbytes, + loff_t off, struct page_counter *pc, + struct list_head *watchers) +{ + unsigned long usage; + struct cgroup_of_peak *peer_ctx; + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + struct cgroup_of_peak *ofp = of_peak(of); - switch (get_mctgt_type(vma, addr, ptent, &target)) { - case MC_TARGET_DEVICE: - device = true; - /* fall through */ - case MC_TARGET_PAGE: - page = target.page; - /* - * We can have a part of the split pmd here. Moving it - * can be done but it would be too convoluted so simply - * ignore such a partial THP and keep it in original - * memcg. There should be somebody mapping the head. - */ - if (PageTransCompound(page)) - goto put; - if (!device && isolate_lru_page(page)) - goto put; - if (!mem_cgroup_move_account(page, false, - mc.from, mc.to)) { - mc.precharge--; - /* we uncharge from mc.from later. */ - mc.moved_charge++; - } - if (!device) - putback_lru_page(page); -put: /* get_mctgt_type() gets the page */ - put_page(page); - break; - case MC_TARGET_SWAP: - ent = target.ent; - if (!mem_cgroup_move_swap_account(ent, mc.from, mc.to)) { - mc.precharge--; - /* we fixup refcnts and charges later. */ - mc.moved_swap++; - } - break; - default: - break; - } - } - pte_unmap_unlock(pte - 1, ptl); - cond_resched(); + spin_lock(&memcg->peaks_lock); - if (addr != end) { - /* - * We have consumed all precharges we got in can_attach(). - * We try charge one by one, but don't do any additional - * charges to mc.to if we have failed in charge once in attach() - * phase. - */ - ret = mem_cgroup_do_precharge(1); - if (!ret) - goto retry; - } + usage = page_counter_read(pc); + WRITE_ONCE(pc->local_watermark, usage); - return ret; -} + list_for_each_entry(peer_ctx, watchers, list) + if (usage > peer_ctx->value) + WRITE_ONCE(peer_ctx->value, usage); -static void mem_cgroup_move_charge(void) -{ - struct mm_walk mem_cgroup_move_charge_walk = { - .pmd_entry = mem_cgroup_move_charge_pte_range, - .mm = mc.mm, - }; + /* initial write, register watcher */ + if (ofp->value == OFP_PEAK_UNSET) + list_add(&ofp->list, watchers); - lru_add_drain_all(); - /* - * Signal lock_page_memcg() to take the memcg's move_lock - * while we're moving its pages to another memcg. Then wait - * for already started RCU-only updates to finish. - */ - atomic_inc(&mc.from->moving_account); - synchronize_rcu(); -retry: - if (unlikely(!down_read_trylock(&mc.mm->mmap_sem))) { - /* - * Someone who are holding the mmap_sem might be waiting in - * waitq. So we cancel all extra charges, wake up all waiters, - * and retry. Because we cancel precharges, we might not be able - * to move enough charges, but moving charge is a best-effort - * feature anyway, so it wouldn't be a big problem. - */ - __mem_cgroup_clear_mc(); - cond_resched(); - goto retry; - } - /* - * When we have consumed all precharges and failed in doing - * additional charge, the page walk just aborts. - */ - walk_page_range(0, mc.mm->highest_vm_end, &mem_cgroup_move_charge_walk); + WRITE_ONCE(ofp->value, usage); + spin_unlock(&memcg->peaks_lock); - up_read(&mc.mm->mmap_sem); - atomic_dec(&mc.from->moving_account); + return nbytes; } -static void mem_cgroup_move_task(void) -{ - if (mc.to) { - mem_cgroup_move_charge(); - mem_cgroup_clear_mc(); - } -} -#else /* !CONFIG_MMU */ -static int mem_cgroup_can_attach(struct cgroup_taskset *tset) -{ - return 0; -} -static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) +static ssize_t memory_peak_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) { -} -static void mem_cgroup_move_task(void) -{ -} -#endif + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); -/* - * Cgroup retains root cgroups across [un]mount cycles making it necessary - * to verify whether we're attached to the default hierarchy on each mount - * attempt. - */ -static void mem_cgroup_bind(struct cgroup_subsys_state *root_css) -{ - /* - * use_hierarchy is forced on the default hierarchy. cgroup core - * guarantees that @root doesn't have any children, so turning it - * on for the root memcg is enough. - */ - if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) - root_mem_cgroup->use_hierarchy = true; - else - root_mem_cgroup->use_hierarchy = false; + return peak_write(of, buf, nbytes, off, &memcg->memory, + &memcg->memory_peaks); } -static u64 memory_current_read(struct cgroup_subsys_state *css, - struct cftype *cft) -{ - struct mem_cgroup *memcg = mem_cgroup_from_css(css); - - return (u64)page_counter_read(&memcg->memory) * PAGE_SIZE; -} +#undef OFP_PEAK_UNSET static int memory_min_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - unsigned long min = READ_ONCE(memcg->memory.min); - - if (min == PAGE_COUNTER_MAX) - seq_puts(m, "max\n"); - else - seq_printf(m, "%llu\n", (u64)min * PAGE_SIZE); - - return 0; + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->memory.min)); } static ssize_t memory_min_write(struct kernfs_open_file *of, @@ -5394,15 +4344,8 @@ static ssize_t memory_min_write(struct kernfs_open_file *of, static int memory_low_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - unsigned long low = READ_ONCE(memcg->memory.low); - - if (low == PAGE_COUNTER_MAX) - seq_puts(m, "max\n"); - else - seq_printf(m, "%llu\n", (u64)low * PAGE_SIZE); - - return 0; + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->memory.low)); } static ssize_t memory_low_write(struct kernfs_open_file *of, @@ -5424,22 +4367,16 @@ static ssize_t memory_low_write(struct kernfs_open_file *of, static int memory_high_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - unsigned long high = READ_ONCE(memcg->high); - - if (high == PAGE_COUNTER_MAX) - seq_puts(m, "max\n"); - else - seq_printf(m, "%llu\n", (u64)high * PAGE_SIZE); - - return 0; + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->memory.high)); } static ssize_t memory_high_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); - unsigned long nr_pages; + unsigned int nr_retries = MAX_RECLAIM_RETRIES; + bool drained = false; unsigned long high; int err; @@ -5448,35 +4385,49 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, if (err) return err; - memcg->high = high; + page_counter_set_high(&memcg->memory, high); + + if (of->file->f_flags & O_NONBLOCK) + goto out; + + for (;;) { + unsigned long nr_pages = page_counter_read(&memcg->memory); + unsigned long reclaimed; + + if (nr_pages <= high) + break; + + if (signal_pending(current)) + break; + + if (!drained) { + drain_all_stock(memcg); + drained = true; + continue; + } - nr_pages = page_counter_read(&memcg->memory); - if (nr_pages > high) - try_to_free_mem_cgroup_pages(memcg, nr_pages - high, - GFP_KERNEL, true); + reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high, + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, NULL); + if (!reclaimed && !nr_retries--) + break; + } +out: memcg_wb_domain_size_changed(memcg); return nbytes; } static int memory_max_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - unsigned long max = READ_ONCE(memcg->memory.max); - - if (max == PAGE_COUNTER_MAX) - seq_puts(m, "max\n"); - else - seq_printf(m, "%llu\n", (u64)max * PAGE_SIZE); - - return 0; + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->memory.max)); } static ssize_t memory_max_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); - unsigned int nr_reclaims = MEM_CGROUP_RECLAIM_RETRIES; + unsigned int nr_reclaims = MAX_RECLAIM_RETRIES; bool drained = false; unsigned long max; int err; @@ -5488,16 +4439,17 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, xchg(&memcg->memory.max, max); + if (of->file->f_flags & O_NONBLOCK) + goto out; + for (;;) { unsigned long nr_pages = page_counter_read(&memcg->memory); if (nr_pages <= max) break; - if (signal_pending(current)) { - err = -EINTR; + if (signal_pending(current)) break; - } if (!drained) { drain_all_stock(memcg); @@ -5507,7 +4459,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, if (nr_reclaims) { if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max, - GFP_KERNEL, true)) + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, NULL)) nr_reclaims--; continue; } @@ -5515,112 +4467,105 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, memcg_memory_event(memcg, MEMCG_OOM); if (!mem_cgroup_out_of_memory(memcg, GFP_KERNEL, 0)) break; + cond_resched(); } - +out: memcg_wb_domain_size_changed(memcg); return nbytes; } +/* + * Note: don't forget to update the 'samples/cgroup/memcg_event_listener' + * if any new events become available. + */ +static void __memory_events_show(struct seq_file *m, atomic_long_t *events) +{ + seq_printf(m, "low %lu\n", atomic_long_read(&events[MEMCG_LOW])); + seq_printf(m, "high %lu\n", atomic_long_read(&events[MEMCG_HIGH])); + seq_printf(m, "max %lu\n", atomic_long_read(&events[MEMCG_MAX])); + seq_printf(m, "oom %lu\n", atomic_long_read(&events[MEMCG_OOM])); + seq_printf(m, "oom_kill %lu\n", + atomic_long_read(&events[MEMCG_OOM_KILL])); + seq_printf(m, "oom_group_kill %lu\n", + atomic_long_read(&events[MEMCG_OOM_GROUP_KILL])); + seq_printf(m, "sock_throttled %lu\n", + atomic_long_read(&events[MEMCG_SOCK_THROTTLED])); +} + static int memory_events_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); - seq_printf(m, "low %lu\n", - atomic_long_read(&memcg->memory_events[MEMCG_LOW])); - seq_printf(m, "high %lu\n", - atomic_long_read(&memcg->memory_events[MEMCG_HIGH])); - seq_printf(m, "max %lu\n", - atomic_long_read(&memcg->memory_events[MEMCG_MAX])); - seq_printf(m, "oom %lu\n", - atomic_long_read(&memcg->memory_events[MEMCG_OOM])); - seq_printf(m, "oom_kill %lu\n", - atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL])); + __memory_events_show(m, memcg->memory_events); + return 0; +} +static int memory_events_local_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + + __memory_events_show(m, memcg->memory_events_local); + return 0; +} + +int memory_stat_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + char *buf = kmalloc(SEQ_BUF_SIZE, GFP_KERNEL); + struct seq_buf s; + + if (!buf) + return -ENOMEM; + seq_buf_init(&s, buf, SEQ_BUF_SIZE); + memory_stat_format(memcg, &s); + seq_puts(m, buf); + kfree(buf); return 0; } -static int memory_stat_show(struct seq_file *m, void *v) +#ifdef CONFIG_NUMA +static inline unsigned long lruvec_page_state_output(struct lruvec *lruvec, + int item) +{ + return lruvec_page_state(lruvec, item) * + memcg_page_state_output_unit(item); +} + +static int memory_numa_stat_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - struct accumulated_stats acc; int i; + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); - /* - * Provide statistics on the state of the memory subsystem as - * well as cumulative event counters that show past behavior. - * - * This list is ordered following a combination of these gradients: - * 1) generic big picture -> specifics and details - * 2) reflecting userspace activity -> reflecting kernel heuristics - * - * Current memory state: - */ + mem_cgroup_flush_stats(memcg); - memset(&acc, 0, sizeof(acc)); - acc.stats_size = MEMCG_NR_STAT; - acc.events_size = NR_VM_EVENT_ITEMS; - accumulate_memcg_tree(memcg, &acc); - - seq_printf(m, "anon %llu\n", - (u64)acc.stat[MEMCG_RSS] * PAGE_SIZE); - seq_printf(m, "file %llu\n", - (u64)acc.stat[MEMCG_CACHE] * PAGE_SIZE); - seq_printf(m, "kernel_stack %llu\n", - (u64)acc.stat[MEMCG_KERNEL_STACK_KB] * 1024); - seq_printf(m, "slab %llu\n", - (u64)(acc.stat[NR_SLAB_RECLAIMABLE] + - acc.stat[NR_SLAB_UNRECLAIMABLE]) * PAGE_SIZE); - seq_printf(m, "sock %llu\n", - (u64)acc.stat[MEMCG_SOCK] * PAGE_SIZE); - - seq_printf(m, "shmem %llu\n", - (u64)acc.stat[NR_SHMEM] * PAGE_SIZE); - seq_printf(m, "file_mapped %llu\n", - (u64)acc.stat[NR_FILE_MAPPED] * PAGE_SIZE); - seq_printf(m, "file_dirty %llu\n", - (u64)acc.stat[NR_FILE_DIRTY] * PAGE_SIZE); - seq_printf(m, "file_writeback %llu\n", - (u64)acc.stat[NR_WRITEBACK] * PAGE_SIZE); - - for (i = 0; i < NR_LRU_LISTS; i++) - seq_printf(m, "%s %llu\n", mem_cgroup_lru_names[i], - (u64)acc.lru_pages[i] * PAGE_SIZE); - - seq_printf(m, "slab_reclaimable %llu\n", - (u64)acc.stat[NR_SLAB_RECLAIMABLE] * PAGE_SIZE); - seq_printf(m, "slab_unreclaimable %llu\n", - (u64)acc.stat[NR_SLAB_UNRECLAIMABLE] * PAGE_SIZE); + for (i = 0; i < ARRAY_SIZE(memory_stats); i++) { + int nid; - /* Accumulated memory events */ + if (memory_stats[i].idx >= NR_VM_NODE_STAT_ITEMS) + continue; + + seq_printf(m, "%s", memory_stats[i].name); + for_each_node_state(nid, N_MEMORY) { + u64 size; + struct lruvec *lruvec; - seq_printf(m, "pgfault %lu\n", acc.events[PGFAULT]); - seq_printf(m, "pgmajfault %lu\n", acc.events[PGMAJFAULT]); - - seq_printf(m, "workingset_refault %lu\n", - acc.stat[WORKINGSET_REFAULT]); - seq_printf(m, "workingset_activate %lu\n", - acc.stat[WORKINGSET_ACTIVATE]); - seq_printf(m, "workingset_nodereclaim %lu\n", - acc.stat[WORKINGSET_NODERECLAIM]); - - seq_printf(m, "pgrefill %lu\n", acc.events[PGREFILL]); - seq_printf(m, "pgscan %lu\n", acc.events[PGSCAN_KSWAPD] + - acc.events[PGSCAN_DIRECT]); - seq_printf(m, "pgsteal %lu\n", acc.events[PGSTEAL_KSWAPD] + - acc.events[PGSTEAL_DIRECT]); - seq_printf(m, "pgactivate %lu\n", acc.events[PGACTIVATE]); - seq_printf(m, "pgdeactivate %lu\n", acc.events[PGDEACTIVATE]); - seq_printf(m, "pglazyfree %lu\n", acc.events[PGLAZYFREE]); - seq_printf(m, "pglazyfreed %lu\n", acc.events[PGLAZYFREED]); + lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid)); + size = lruvec_page_state_output(lruvec, + memory_stats[i].idx); + seq_printf(m, " N%d=%llu", nid, size); + } + seq_putc(m, '\n'); + } return 0; } +#endif static int memory_oom_group_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); - seq_printf(m, "%d\n", memcg->oom_group); + seq_printf(m, "%d\n", READ_ONCE(memcg->oom_group)); return 0; } @@ -5642,7 +4587,20 @@ static ssize_t memory_oom_group_write(struct kernfs_open_file *of, if (oom_group != 0 && oom_group != 1) return -EINVAL; - memcg->oom_group = oom_group; + WRITE_ONCE(memcg->oom_group, oom_group); + + return nbytes; +} + +static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + int ret; + + ret = user_proactive_reclaim(buf, memcg, NULL); + if (ret) + return ret; return nbytes; } @@ -5654,6 +4612,14 @@ static struct cftype memory_files[] = { .read_u64 = memory_current_read, }, { + .name = "peak", + .flags = CFTYPE_NOT_ON_ROOT, + .open = peak_open, + .release = peak_release, + .seq_show = memory_peak_show, + .write = memory_peak_write, + }, + { .name = "min", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = memory_min_show, @@ -5684,16 +4650,32 @@ static struct cftype memory_files[] = { .seq_show = memory_events_show, }, { - .name = "stat", + .name = "events.local", .flags = CFTYPE_NOT_ON_ROOT, + .file_offset = offsetof(struct mem_cgroup, events_local_file), + .seq_show = memory_events_local_show, + }, + { + .name = "stat", .seq_show = memory_stat_show, }, +#ifdef CONFIG_NUMA + { + .name = "numa_stat", + .seq_show = memory_numa_stat_show, + }, +#endif { .name = "oom.group", .flags = CFTYPE_NOT_ON_ROOT | CFTYPE_NS_DELEGATABLE, .seq_show = memory_oom_group_show, .write = memory_oom_group_write, }, + { + .name = "reclaim", + .flags = CFTYPE_NS_DELEGATABLE, + .write = memory_reclaim, + }, { } /* terminate */ }; @@ -5704,321 +4686,143 @@ struct cgroup_subsys memory_cgrp_subsys = { .css_released = mem_cgroup_css_released, .css_free = mem_cgroup_css_free, .css_reset = mem_cgroup_css_reset, - .can_attach = mem_cgroup_can_attach, - .cancel_attach = mem_cgroup_cancel_attach, - .post_attach = mem_cgroup_move_task, - .bind = mem_cgroup_bind, + .css_rstat_flush = mem_cgroup_css_rstat_flush, + .attach = mem_cgroup_attach, + .fork = mem_cgroup_fork, + .exit = mem_cgroup_exit, .dfl_cftypes = memory_files, +#ifdef CONFIG_MEMCG_V1 .legacy_cftypes = mem_cgroup_legacy_files, +#endif .early_init = 0, }; /** - * mem_cgroup_protected - check if memory consumption is in the normal range + * mem_cgroup_calculate_protection - check if memory consumption is in the normal range * @root: the top ancestor of the sub-tree being checked * @memcg: the memory cgroup to check * * WARNING: This function is not stateless! It can only be used as part * of a top-down tree iteration, not for isolated queries. - * - * Returns one of the following: - * MEMCG_PROT_NONE: cgroup memory is not protected - * MEMCG_PROT_LOW: cgroup memory is protected as long there is - * an unprotected supply of reclaimable memory from other cgroups. - * MEMCG_PROT_MIN: cgroup memory is protected - * - * @root is exclusive; it is never protected when looked at directly - * - * To provide a proper hierarchical behavior, effective memory.min/low values - * are used. Below is the description of how effective memory.low is calculated. - * Effective memory.min values is calculated in the same way. - * - * Effective memory.low is always equal or less than the original memory.low. - * If there is no memory.low overcommittment (which is always true for - * top-level memory cgroups), these two values are equal. - * Otherwise, it's a part of parent's effective memory.low, - * calculated as a cgroup's memory.low usage divided by sum of sibling's - * memory.low usages, where memory.low usage is the size of actually - * protected memory. - * - * low_usage - * elow = min( memory.low, parent->elow * ------------------ ), - * siblings_low_usage - * - * | memory.current, if memory.current < memory.low - * low_usage = | - | 0, otherwise. - * - * - * Such definition of the effective memory.low provides the expected - * hierarchical behavior: parent's memory.low value is limiting - * children, unprotected memory is reclaimed first and cgroups, - * which are not using their guarantee do not affect actual memory - * distribution. - * - * For example, if there are memcgs A, A/B, A/C, A/D and A/E: - * - * A A/memory.low = 2G, A/memory.current = 6G - * //\\ - * BC DE B/memory.low = 3G B/memory.current = 2G - * C/memory.low = 1G C/memory.current = 2G - * D/memory.low = 0 D/memory.current = 2G - * E/memory.low = 10G E/memory.current = 0 - * - * and the memory pressure is applied, the following memory distribution - * is expected (approximately): - * - * A/memory.current = 2G - * - * B/memory.current = 1.3G - * C/memory.current = 0.6G - * D/memory.current = 0 - * E/memory.current = 0 - * - * These calculations require constant tracking of the actual low usages - * (see propagate_protected_usage()), as well as recursive calculation of - * effective memory.low values. But as we do call mem_cgroup_protected() - * path for each memory cgroup top-down from the reclaim, - * it's possible to optimize this part, and save calculated elow - * for next usage. This part is intentionally racy, but it's ok, - * as memory.low is a best-effort mechanism. */ -enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, - struct mem_cgroup *memcg) +void mem_cgroup_calculate_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg) { - struct mem_cgroup *parent; - unsigned long emin, parent_emin; - unsigned long elow, parent_elow; - unsigned long usage; + bool recursive_protection = + cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT; if (mem_cgroup_disabled()) - return MEMCG_PROT_NONE; + return; if (!root) root = root_mem_cgroup; - if (memcg == root) - return MEMCG_PROT_NONE; - usage = page_counter_read(&memcg->memory); - if (!usage) - return MEMCG_PROT_NONE; - - emin = memcg->memory.min; - elow = memcg->memory.low; - - parent = parent_mem_cgroup(memcg); - /* No parent means a non-hierarchical mode on v1 memcg */ - if (!parent) - return MEMCG_PROT_NONE; - - if (parent == root) - goto exit; - - parent_emin = READ_ONCE(parent->memory.emin); - emin = min(emin, parent_emin); - if (emin && parent_emin) { - unsigned long min_usage, siblings_min_usage; - - min_usage = min(usage, memcg->memory.min); - siblings_min_usage = atomic_long_read( - &parent->memory.children_min_usage); - - if (min_usage && siblings_min_usage) - emin = min(emin, parent_emin * min_usage / - siblings_min_usage); - } - - parent_elow = READ_ONCE(parent->memory.elow); - elow = min(elow, parent_elow); - if (elow && parent_elow) { - unsigned long low_usage, siblings_low_usage; - - low_usage = min(usage, memcg->memory.low); - siblings_low_usage = atomic_long_read( - &parent->memory.children_low_usage); - - if (low_usage && siblings_low_usage) - elow = min(elow, parent_elow * low_usage / - siblings_low_usage); - } - -exit: - memcg->memory.emin = emin; - memcg->memory.elow = elow; - - if (usage <= emin) - return MEMCG_PROT_MIN; - else if (usage <= elow) - return MEMCG_PROT_LOW; - else - return MEMCG_PROT_NONE; + page_counter_calculate_protection(&root->memory, &memcg->memory, recursive_protection); } -/** - * mem_cgroup_try_charge - try charging a page - * @page: page to charge - * @mm: mm context of the victim - * @gfp_mask: reclaim mode - * @memcgp: charged memcg return - * @compound: charge the page as compound or small page - * - * Try to charge @page to the memcg that @mm belongs to, reclaiming - * pages according to @gfp_mask if necessary. - * - * Returns 0 on success, with *@memcgp pointing to the charged memcg. - * Otherwise, an error code is returned. - * - * After page->mapping has been set up, the caller must finalize the - * charge with mem_cgroup_commit_charge(). Or abort the transaction - * with mem_cgroup_cancel_charge() in case page instantiation fails. - */ -int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound) +static int charge_memcg(struct folio *folio, struct mem_cgroup *memcg, + gfp_t gfp) { - struct mem_cgroup *memcg = NULL; - unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; - int ret = 0; + int ret; - if (mem_cgroup_disabled()) + ret = try_charge(memcg, gfp, folio_nr_pages(folio)); + if (ret) goto out; - if (PageSwapCache(page)) { - /* - * Every swap fault against a single page tries to charge the - * page, bail as early as possible. shmem_unuse() encounters - * already charged pages, too. The USED bit is protected by - * the page lock, which serializes swap cache removal, which - * in turn serializes uncharging. - */ - VM_BUG_ON_PAGE(!PageLocked(page), page); - if (compound_head(page)->mem_cgroup) - goto out; - - if (do_swap_account) { - swp_entry_t ent = { .val = page_private(page), }; - unsigned short id = lookup_swap_cgroup_id(ent); - - rcu_read_lock(); - memcg = mem_cgroup_from_id(id); - if (memcg && !css_tryget_online(&memcg->css)) - memcg = NULL; - rcu_read_unlock(); - } - } - - if (!memcg) - memcg = get_mem_cgroup_from_mm(mm); - - ret = try_charge(memcg, gfp_mask, nr_pages); - - css_put(&memcg->css); + css_get(&memcg->css); + commit_charge(folio, memcg); + memcg1_commit_charge(folio, memcg); out: - *memcgp = memcg; return ret; } -int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp, - bool compound) +int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { struct mem_cgroup *memcg; int ret; - ret = mem_cgroup_try_charge(page, mm, gfp_mask, memcgp, compound); - memcg = *memcgp; - mem_cgroup_throttle_swaprate(memcg, page_to_nid(page), gfp_mask); + memcg = get_mem_cgroup_from_mm(mm); + ret = charge_memcg(folio, memcg, gfp); + css_put(&memcg->css); + return ret; } /** - * mem_cgroup_commit_charge - commit a page charge - * @page: page to charge - * @memcg: memcg to charge the page to - * @lrucare: page might be on LRU already - * @compound: charge the page as compound or small page - * - * Finalize a charge transaction started by mem_cgroup_try_charge(), - * after page->mapping has been set up. This must happen atomically - * as part of the page instantiation, i.e. under the page table lock - * for anonymous pages, under the page lock for page and swap cache. + * mem_cgroup_charge_hugetlb - charge the memcg for a hugetlb folio + * @folio: folio being charged + * @gfp: reclaim mode * - * In addition, the page must not be on the LRU during the commit, to - * prevent racing with task migration. If it might be, use @lrucare. + * This function is called when allocating a huge page folio, after the page has + * already been obtained and charged to the appropriate hugetlb cgroup + * controller (if it is enabled). * - * Use mem_cgroup_cancel_charge() to cancel the transaction instead. + * Returns ENOMEM if the memcg is already full. + * Returns 0 if either the charge was successful, or if we skip the charging. */ -void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare, bool compound) +int mem_cgroup_charge_hugetlb(struct folio *folio, gfp_t gfp) { - unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; - - VM_BUG_ON_PAGE(!page->mapping, page); - VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); + struct mem_cgroup *memcg = get_mem_cgroup_from_current(); + int ret = 0; - if (mem_cgroup_disabled()) - return; /* - * Swap faults will attempt to charge the same page multiple - * times. But reuse_swap_page() might have removed the page - * from swapcache already, so we can't check PageSwapCache(). + * Even memcg does not account for hugetlb, we still want to update + * system-level stats via lruvec_stat_mod_folio. Return 0, and skip + * charging the memcg. */ - if (!memcg) - return; - - commit_charge(page, memcg, lrucare); + if (mem_cgroup_disabled() || !memcg_accounts_hugetlb() || + !memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) + goto out; - local_irq_disable(); - mem_cgroup_charge_statistics(memcg, page, compound, nr_pages); - memcg_check_events(memcg, page); - local_irq_enable(); + if (charge_memcg(folio, memcg, gfp)) + ret = -ENOMEM; - if (do_memsw_account() && PageSwapCache(page)) { - swp_entry_t entry = { .val = page_private(page) }; - /* - * The swap entry might not get freed for a long time, - * let's not wait for it. The page already received a - * memory+swap charge, drop the swap entry duplicate. - */ - mem_cgroup_uncharge_swap(entry, nr_pages); - } +out: + mem_cgroup_put(memcg); + return ret; } /** - * mem_cgroup_cancel_charge - cancel a page charge - * @page: page to charge - * @memcg: memcg to charge the page to - * @compound: charge the page as compound or small page + * mem_cgroup_swapin_charge_folio - Charge a newly allocated folio for swapin. + * @folio: folio to charge. + * @mm: mm context of the victim + * @gfp: reclaim mode + * @entry: swap entry for which the folio is allocated * - * Cancel a charge transaction started by mem_cgroup_try_charge(). + * This function charges a folio allocated for swapin. Please call this before + * adding the folio to the swapcache. + * + * Returns 0 on success. Otherwise, an error code is returned. */ -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, - bool compound) +int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, + gfp_t gfp, swp_entry_t entry) { - unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; + struct mem_cgroup *memcg; + unsigned short id; + int ret; if (mem_cgroup_disabled()) - return; - /* - * Swap faults will attempt to charge the same page multiple - * times. But reuse_swap_page() might have removed the page - * from swapcache already, so we can't check PageSwapCache(). - */ - if (!memcg) - return; + return 0; + + id = lookup_swap_cgroup_id(entry); + rcu_read_lock(); + memcg = mem_cgroup_from_id(id); + if (!memcg || !css_tryget_online(&memcg->css)) + memcg = get_mem_cgroup_from_mm(mm); + rcu_read_unlock(); - cancel_charge(memcg, nr_pages); + ret = charge_memcg(folio, memcg, gfp); + + css_put(&memcg->css); + return ret; } struct uncharge_gather { struct mem_cgroup *memcg; + unsigned long nr_memory; unsigned long pgpgout; - unsigned long nr_anon; - unsigned long nr_file; unsigned long nr_kmem; - unsigned long nr_huge; - unsigned long nr_shmem; - struct page *dummy_page; + int nid; }; static inline void uncharge_gather_clear(struct uncharge_gather *ug) @@ -6028,193 +4832,190 @@ static inline void uncharge_gather_clear(struct uncharge_gather *ug) static void uncharge_batch(const struct uncharge_gather *ug) { - unsigned long nr_pages = ug->nr_anon + ug->nr_file + ug->nr_kmem; - unsigned long flags; - - if (!mem_cgroup_is_root(ug->memcg)) { - page_counter_uncharge(&ug->memcg->memory, nr_pages); - if (do_memsw_account()) - page_counter_uncharge(&ug->memcg->memsw, nr_pages); - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && ug->nr_kmem) - page_counter_uncharge(&ug->memcg->kmem, ug->nr_kmem); - memcg_oom_recover(ug->memcg); + if (ug->nr_memory) { + memcg_uncharge(ug->memcg, ug->nr_memory); + if (ug->nr_kmem) { + mod_memcg_state(ug->memcg, MEMCG_KMEM, -ug->nr_kmem); + memcg1_account_kmem(ug->memcg, -ug->nr_kmem); + } + memcg1_oom_recover(ug->memcg); } - local_irq_save(flags); - __mod_memcg_state(ug->memcg, MEMCG_RSS, -ug->nr_anon); - __mod_memcg_state(ug->memcg, MEMCG_CACHE, -ug->nr_file); - __mod_memcg_state(ug->memcg, MEMCG_RSS_HUGE, -ug->nr_huge); - __mod_memcg_state(ug->memcg, NR_SHMEM, -ug->nr_shmem); - __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); - __this_cpu_add(ug->memcg->stat_cpu->nr_page_events, nr_pages); - memcg_check_events(ug->memcg, ug->dummy_page); - local_irq_restore(flags); + memcg1_uncharge_batch(ug->memcg, ug->pgpgout, ug->nr_memory, ug->nid); - if (!mem_cgroup_is_root(ug->memcg)) - css_put_many(&ug->memcg->css, nr_pages); + /* drop reference from uncharge_folio */ + css_put(&ug->memcg->css); } -static void uncharge_page(struct page *page, struct uncharge_gather *ug) +static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) { - VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON_PAGE(page_count(page) && !is_zone_device_page(page) && - !PageHWPoison(page) , page); + long nr_pages; + struct mem_cgroup *memcg; + struct obj_cgroup *objcg; - if (!page->mem_cgroup) - return; + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* * Nobody should be changing or seriously looking at - * page->mem_cgroup at this point, we have fully - * exclusive access to the page. + * folio memcg or objcg at this point, we have fully + * exclusive access to the folio. */ + if (folio_memcg_kmem(folio)) { + objcg = __folio_objcg(folio); + /* + * This get matches the put at the end of the function and + * kmem pages do not hold memcg references anymore. + */ + memcg = get_mem_cgroup_from_objcg(objcg); + } else { + memcg = __folio_memcg(folio); + } - if (ug->memcg != page->mem_cgroup) { + if (!memcg) + return; + + if (ug->memcg != memcg) { if (ug->memcg) { uncharge_batch(ug); uncharge_gather_clear(ug); } - ug->memcg = page->mem_cgroup; + ug->memcg = memcg; + ug->nid = folio_nid(folio); + + /* pairs with css_put in uncharge_batch */ + css_get(&memcg->css); } - if (!PageKmemcg(page)) { - unsigned int nr_pages = 1; + nr_pages = folio_nr_pages(folio); - if (PageTransHuge(page)) { - nr_pages <<= compound_order(page); - ug->nr_huge += nr_pages; - } - if (PageAnon(page)) - ug->nr_anon += nr_pages; - else { - ug->nr_file += nr_pages; - if (PageSwapBacked(page)) - ug->nr_shmem += nr_pages; - } - ug->pgpgout++; + if (folio_memcg_kmem(folio)) { + ug->nr_memory += nr_pages; + ug->nr_kmem += nr_pages; + + folio->memcg_data = 0; + obj_cgroup_put(objcg); } else { - ug->nr_kmem += 1 << compound_order(page); - __ClearPageKmemcg(page); + /* LRU pages aren't accounted at the root level */ + if (!mem_cgroup_is_root(memcg)) + ug->nr_memory += nr_pages; + ug->pgpgout++; + + WARN_ON_ONCE(folio_unqueue_deferred_split(folio)); + folio->memcg_data = 0; } - ug->dummy_page = page; - page->mem_cgroup = NULL; + css_put(&memcg->css); } -static void uncharge_list(struct list_head *page_list) +void __mem_cgroup_uncharge(struct folio *folio) { struct uncharge_gather ug; - struct list_head *next; - uncharge_gather_clear(&ug); - - /* - * Note that the list can be a single page->lru; hence the - * do-while loop instead of a simple list_for_each_entry(). - */ - next = page_list->next; - do { - struct page *page; + /* Don't touch folio->lru of any random page, pre-check: */ + if (!folio_memcg_charged(folio)) + return; - page = list_entry(next, struct page, lru); - next = page->lru.next; + uncharge_gather_clear(&ug); + uncharge_folio(folio, &ug); + uncharge_batch(&ug); +} - uncharge_page(page, &ug); - } while (next != page_list); +void __mem_cgroup_uncharge_folios(struct folio_batch *folios) +{ + struct uncharge_gather ug; + unsigned int i; + uncharge_gather_clear(&ug); + for (i = 0; i < folios->nr; i++) + uncharge_folio(folios->folios[i], &ug); if (ug.memcg) uncharge_batch(&ug); } /** - * mem_cgroup_uncharge - uncharge a page - * @page: page to uncharge + * mem_cgroup_replace_folio - Charge a folio's replacement. + * @old: Currently circulating folio. + * @new: Replacement folio. * - * Uncharge a page previously charged with mem_cgroup_try_charge() and - * mem_cgroup_commit_charge(). + * Charge @new as a replacement folio for @old. @old will + * be uncharged upon free. + * + * Both folios must be locked, @new->mapping must be set up. */ -void mem_cgroup_uncharge(struct page *page) +void mem_cgroup_replace_folio(struct folio *old, struct folio *new) { - struct uncharge_gather ug; + struct mem_cgroup *memcg; + long nr_pages = folio_nr_pages(new); + + VM_BUG_ON_FOLIO(!folio_test_locked(old), old); + VM_BUG_ON_FOLIO(!folio_test_locked(new), new); + VM_BUG_ON_FOLIO(folio_test_anon(old) != folio_test_anon(new), new); + VM_BUG_ON_FOLIO(folio_nr_pages(old) != nr_pages, new); if (mem_cgroup_disabled()) return; - /* Don't touch page->lru of any random page, pre-check: */ - if (!page->mem_cgroup) + /* Page cache replacement: new folio already charged? */ + if (folio_memcg_charged(new)) return; - uncharge_gather_clear(&ug); - uncharge_page(page, &ug); - uncharge_batch(&ug); -} - -/** - * mem_cgroup_uncharge_list - uncharge a list of page - * @page_list: list of pages to uncharge - * - * Uncharge a list of pages previously charged with - * mem_cgroup_try_charge() and mem_cgroup_commit_charge(). - */ -void mem_cgroup_uncharge_list(struct list_head *page_list) -{ - if (mem_cgroup_disabled()) + memcg = folio_memcg(old); + VM_WARN_ON_ONCE_FOLIO(!memcg, old); + if (!memcg) return; - if (!list_empty(page_list)) - uncharge_list(page_list); + /* Force-charge the new page. The old one will be freed soon */ + if (!mem_cgroup_is_root(memcg)) { + page_counter_charge(&memcg->memory, nr_pages); + if (do_memsw_account()) + page_counter_charge(&memcg->memsw, nr_pages); + } + + css_get(&memcg->css); + commit_charge(new, memcg); + memcg1_commit_charge(new, memcg); } /** - * mem_cgroup_migrate - charge a page's replacement - * @oldpage: currently circulating page - * @newpage: replacement page + * mem_cgroup_migrate - Transfer the memcg data from the old to the new folio. + * @old: Currently circulating folio. + * @new: Replacement folio. * - * Charge @newpage as a replacement page for @oldpage. @oldpage will - * be uncharged upon free. + * Transfer the memcg data from the old folio to the new folio for migration. + * The old folio's data info will be cleared. Note that the memory counters + * will remain unchanged throughout the process. * - * Both pages must be locked, @newpage->mapping must be set up. + * Both folios must be locked, @new->mapping must be set up. */ -void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) +void mem_cgroup_migrate(struct folio *old, struct folio *new) { struct mem_cgroup *memcg; - unsigned int nr_pages; - bool compound; - unsigned long flags; - VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); - VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); - VM_BUG_ON_PAGE(PageAnon(oldpage) != PageAnon(newpage), newpage); - VM_BUG_ON_PAGE(PageTransHuge(oldpage) != PageTransHuge(newpage), - newpage); + VM_BUG_ON_FOLIO(!folio_test_locked(old), old); + VM_BUG_ON_FOLIO(!folio_test_locked(new), new); + VM_BUG_ON_FOLIO(folio_test_anon(old) != folio_test_anon(new), new); + VM_BUG_ON_FOLIO(folio_nr_pages(old) != folio_nr_pages(new), new); + VM_BUG_ON_FOLIO(folio_test_lru(old), old); if (mem_cgroup_disabled()) return; - /* Page cache replacement: new page already charged? */ - if (newpage->mem_cgroup) - return; - - /* Swapcache readahead pages can get replaced before being charged */ - memcg = oldpage->mem_cgroup; + memcg = folio_memcg(old); + /* + * Note that it is normal to see !memcg for a hugetlb folio. + * For e.g, itt could have been allocated when memory_hugetlb_accounting + * was not selected. + */ + VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(old) && !memcg, old); if (!memcg) return; - /* Force-charge the new page. The old one will be freed soon */ - compound = PageTransHuge(newpage); - nr_pages = compound ? hpage_nr_pages(newpage) : 1; + /* Transfer the charge and the css ref */ + commit_charge(new, memcg); - page_counter_charge(&memcg->memory, nr_pages); - if (do_memsw_account()) - page_counter_charge(&memcg->memsw, nr_pages); - css_get_many(&memcg->css, nr_pages); - - commit_charge(newpage, memcg, false); - - local_irq_save(flags); - mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages); - memcg_check_events(memcg, newpage); - local_irq_restore(flags); + /* Warning should never happen, so don't worry about refcount non-0 */ + WARN_ON_ONCE(folio_unqueue_deferred_split(old)); + old->memcg_data = 0; } DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key); @@ -6227,27 +5028,17 @@ void mem_cgroup_sk_alloc(struct sock *sk) if (!mem_cgroup_sockets_enabled) return; - /* - * Socket cloning can throw us here with sk_memcg already - * filled. It won't however, necessarily happen from - * process context. So the test for root memcg given - * the current task's memcg won't help us in this case. - * - * Respecting the original socket's memcg is a better - * decision in this case. - */ - if (sk->sk_memcg) { - css_get(&sk->sk_memcg->css); + /* Do not associate the sock with unrelated interrupted task's memcg. */ + if (!in_task()) return; - } rcu_read_lock(); memcg = mem_cgroup_from_task(current); - if (memcg == root_mem_cgroup) + if (mem_cgroup_is_root(memcg)) goto out; - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !memcg->tcpmem_active) + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !memcg1_tcpmem_active(memcg)) goto out; - if (css_tryget_online(&memcg->css)) + if (css_tryget(&memcg->css)) sk->sk_memcg = memcg; out: rcu_read_unlock(); @@ -6255,56 +5046,64 @@ out: void mem_cgroup_sk_free(struct sock *sk) { - if (sk->sk_memcg) - css_put(&sk->sk_memcg->css); + struct mem_cgroup *memcg = mem_cgroup_from_sk(sk); + + if (memcg) + css_put(&memcg->css); +} + +void mem_cgroup_sk_inherit(const struct sock *sk, struct sock *newsk) +{ + struct mem_cgroup *memcg; + + if (sk->sk_memcg == newsk->sk_memcg) + return; + + mem_cgroup_sk_free(newsk); + + memcg = mem_cgroup_from_sk(sk); + if (memcg) + css_get(&memcg->css); + + newsk->sk_memcg = sk->sk_memcg; } /** - * mem_cgroup_charge_skmem - charge socket memory - * @memcg: memcg to charge + * mem_cgroup_sk_charge - charge socket memory + * @sk: socket in memcg to charge * @nr_pages: number of pages to charge + * @gfp_mask: reclaim mode * * Charges @nr_pages to @memcg. Returns %true if the charge fit within - * @memcg's configured limit, %false if the charge had to be forced. + * @memcg's configured limit, %false if it doesn't. */ -bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) +bool mem_cgroup_sk_charge(const struct sock *sk, unsigned int nr_pages, + gfp_t gfp_mask) { - gfp_t gfp_mask = GFP_KERNEL; - - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) { - struct page_counter *fail; + struct mem_cgroup *memcg = mem_cgroup_from_sk(sk); - if (page_counter_try_charge(&memcg->tcpmem, nr_pages, &fail)) { - memcg->tcpmem_pressure = 0; - return true; - } - page_counter_charge(&memcg->tcpmem, nr_pages); - memcg->tcpmem_pressure = 1; - return false; - } - - /* Don't block in the packet receive path */ - if (in_softirq()) - gfp_mask = GFP_NOWAIT; - - mod_memcg_state(memcg, MEMCG_SOCK, nr_pages); + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return memcg1_charge_skmem(memcg, nr_pages, gfp_mask); - if (try_charge(memcg, gfp_mask, nr_pages) == 0) + if (try_charge_memcg(memcg, gfp_mask, nr_pages) == 0) { + mod_memcg_state(memcg, MEMCG_SOCK, nr_pages); return true; + } - try_charge(memcg, gfp_mask|__GFP_NOFAIL, nr_pages); return false; } /** - * mem_cgroup_uncharge_skmem - uncharge socket memory - * @memcg: memcg to uncharge + * mem_cgroup_sk_uncharge - uncharge socket memory + * @sk: socket in memcg to uncharge * @nr_pages: number of pages to uncharge */ -void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) +void mem_cgroup_sk_uncharge(const struct sock *sk, unsigned int nr_pages) { + struct mem_cgroup *memcg = mem_cgroup_from_sk(sk); + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) { - page_counter_uncharge(&memcg->tcpmem, nr_pages); + memcg1_uncharge_skmem(memcg, nr_pages); return; } @@ -6324,164 +5123,76 @@ static int __init cgroup_memory(char *s) cgroup_memory_nosocket = true; if (!strcmp(token, "nokmem")) cgroup_memory_nokmem = true; + if (!strcmp(token, "nobpf")) + cgroup_memory_nobpf = true; } - return 0; + return 1; } __setup("cgroup.memory=", cgroup_memory); /* - * subsys_initcall() for memory controller. + * Memory controller init before cgroup_init() initialize root_mem_cgroup. * * Some parts like memcg_hotplug_cpu_dead() have to be initialized from this * context because of lock dependencies (cgroup_lock -> cpu hotplug) but * basically everything that doesn't depend on a specific mem_cgroup structure * should be initialized from here. */ -static int __init mem_cgroup_init(void) +int __init mem_cgroup_init(void) { - int cpu, node; + unsigned int memcg_size; + int cpu; -#ifdef CONFIG_MEMCG_KMEM /* - * Kmem cache creation is mostly done with the slab_mutex held, - * so use a workqueue with limited concurrency to avoid stalling - * all worker threads in case lots of cgroups are created and - * destroyed simultaneously. + * Currently s32 type (can refer to struct batched_lruvec_stat) is + * used for per-memcg-per-cpu caching of per-node statistics. In order + * to work fine, we should make sure that the overfill threshold can't + * exceed S32_MAX / PAGE_SIZE. */ - memcg_kmem_cache_wq = alloc_workqueue("memcg_kmem_cache", 0, 1); - BUG_ON(!memcg_kmem_cache_wq); -#endif + BUILD_BUG_ON(MEMCG_CHARGE_BATCH > S32_MAX / PAGE_SIZE); cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL, memcg_hotplug_cpu_dead); - for_each_possible_cpu(cpu) + for_each_possible_cpu(cpu) { INIT_WORK(&per_cpu_ptr(&memcg_stock, cpu)->work, - drain_local_stock); - - for_each_node(node) { - struct mem_cgroup_tree_per_node *rtpn; - - rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, - node_online(node) ? node : NUMA_NO_NODE); - - rtpn->rb_root = RB_ROOT; - rtpn->rb_rightmost = NULL; - spin_lock_init(&rtpn->lock); - soft_limit_tree.rb_tree_per_node[node] = rtpn; - } - - return 0; -} -subsys_initcall(mem_cgroup_init); - -#ifdef CONFIG_MEMCG_SWAP -static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) -{ - while (!refcount_inc_not_zero(&memcg->id.ref)) { - /* - * The root cgroup cannot be destroyed, so it's refcount must - * always be >= 1. - */ - if (WARN_ON_ONCE(memcg == root_mem_cgroup)) { - VM_BUG_ON(1); - break; - } - memcg = parent_mem_cgroup(memcg); - if (!memcg) - memcg = root_mem_cgroup; + drain_local_memcg_stock); + INIT_WORK(&per_cpu_ptr(&obj_stock, cpu)->work, + drain_local_obj_stock); } - return memcg; -} - -/** - * mem_cgroup_swapout - transfer a memsw charge to swap - * @page: page whose memsw charge to transfer - * @entry: swap entry to move the charge to - * - * Transfer the memsw charge of @page to @entry. - */ -void mem_cgroup_swapout(struct page *page, swp_entry_t entry) -{ - struct mem_cgroup *memcg, *swap_memcg; - unsigned int nr_entries; - unsigned short oldid; - - VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON_PAGE(page_count(page), page); - - if (!do_memsw_account()) - return; - - memcg = page->mem_cgroup; - /* Readahead page, never charged */ - if (!memcg) - return; - - /* - * In case the memcg owning these pages has been offlined and doesn't - * have an ID allocated to it anymore, charge the closest online - * ancestor for the swap instead and transfer the memory+swap charge. - */ - swap_memcg = mem_cgroup_id_get_online(memcg); - nr_entries = hpage_nr_pages(page); - /* Get references for the tail pages, too */ - if (nr_entries > 1) - mem_cgroup_id_get_many(swap_memcg, nr_entries - 1); - oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg), - nr_entries); - VM_BUG_ON_PAGE(oldid, page); - mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries); + memcg_size = struct_size_t(struct mem_cgroup, nodeinfo, nr_node_ids); + memcg_cachep = kmem_cache_create("mem_cgroup", memcg_size, 0, + SLAB_PANIC | SLAB_HWCACHE_ALIGN, NULL); - page->mem_cgroup = NULL; + memcg_pn_cachep = KMEM_CACHE(mem_cgroup_per_node, + SLAB_PANIC | SLAB_HWCACHE_ALIGN); - if (!mem_cgroup_is_root(memcg)) - page_counter_uncharge(&memcg->memory, nr_entries); - - if (memcg != swap_memcg) { - if (!mem_cgroup_is_root(swap_memcg)) - page_counter_charge(&swap_memcg->memsw, nr_entries); - page_counter_uncharge(&memcg->memsw, nr_entries); - } - - /* - * Interrupts should be disabled here because the caller holds the - * i_pages lock which is taken with interrupts-off. It is - * important here to have the interrupts disabled because it is the - * only synchronisation we have for updating the per-CPU variables. - */ - VM_BUG_ON(!irqs_disabled()); - mem_cgroup_charge_statistics(memcg, page, PageTransHuge(page), - -nr_entries); - memcg_check_events(memcg, page); - - if (!mem_cgroup_is_root(memcg)) - css_put_many(&memcg->css, nr_entries); + return 0; } +#ifdef CONFIG_SWAP /** - * mem_cgroup_try_charge_swap - try charging swap space for a page - * @page: page being added to swap + * __mem_cgroup_try_charge_swap - try charging swap space for a folio + * @folio: folio being added to swap * @entry: swap entry to charge * - * Try to charge @page's memcg for the swap space at @entry. + * Try to charge @folio's memcg for the swap space at @entry. * * Returns 0 on success, -ENOMEM on failure. */ -int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) +int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { - unsigned int nr_pages = hpage_nr_pages(page); + unsigned int nr_pages = folio_nr_pages(folio); struct page_counter *counter; struct mem_cgroup *memcg; - unsigned short oldid; - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) || !do_swap_account) + if (do_memsw_account()) return 0; - memcg = page->mem_cgroup; + memcg = folio_memcg(folio); - /* Readahead page, never charged */ + VM_WARN_ON_ONCE_FOLIO(!memcg, folio); if (!memcg) return 0; @@ -6503,35 +5214,32 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) /* Get references for the tail pages, too */ if (nr_pages > 1) mem_cgroup_id_get_many(memcg, nr_pages - 1); - oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg), nr_pages); - VM_BUG_ON_PAGE(oldid, page); mod_memcg_state(memcg, MEMCG_SWAP, nr_pages); + swap_cgroup_record(folio, mem_cgroup_id(memcg), entry); + return 0; } /** - * mem_cgroup_uncharge_swap - uncharge swap space + * __mem_cgroup_uncharge_swap - uncharge swap space * @entry: swap entry to uncharge * @nr_pages: the amount of swap space to uncharge */ -void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) +void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { struct mem_cgroup *memcg; unsigned short id; - if (!do_swap_account) - return; - - id = swap_cgroup_record(entry, 0, nr_pages); + id = swap_cgroup_clear(entry, nr_pages); rcu_read_lock(); memcg = mem_cgroup_from_id(id); if (memcg) { if (!mem_cgroup_is_root(memcg)) { - if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) - page_counter_uncharge(&memcg->swap, nr_pages); - else + if (do_memsw_account()) page_counter_uncharge(&memcg->memsw, nr_pages); + else + page_counter_uncharge(&memcg->swap, nr_pages); } mod_memcg_state(memcg, MEMCG_SWAP, -nr_pages); mem_cgroup_id_put_many(memcg, nr_pages); @@ -6543,53 +5251,53 @@ long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) { long nr_swap_pages = get_nr_swap_pages(); - if (!do_swap_account || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) + if (mem_cgroup_disabled() || do_memsw_account()) return nr_swap_pages; - for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) + for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) nr_swap_pages = min_t(long, nr_swap_pages, READ_ONCE(memcg->swap.max) - page_counter_read(&memcg->swap)); return nr_swap_pages; } -bool mem_cgroup_swap_full(struct page *page) +bool mem_cgroup_swap_full(struct folio *folio) { struct mem_cgroup *memcg; - VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (vm_swap_full()) return true; - if (!do_swap_account || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) + if (do_memsw_account()) return false; - memcg = page->mem_cgroup; + memcg = folio_memcg(folio); if (!memcg) return false; - for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) - if (page_counter_read(&memcg->swap) * 2 >= memcg->swap.max) + for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) { + unsigned long usage = page_counter_read(&memcg->swap); + + if (usage * 2 >= READ_ONCE(memcg->swap.high) || + usage * 2 >= READ_ONCE(memcg->swap.max)) return true; + } return false; } -/* for remember boot option*/ -#ifdef CONFIG_MEMCG_SWAP_ENABLED -static int really_do_swap_account __initdata = 1; -#else -static int really_do_swap_account __initdata; -#endif - -static int __init enable_swap_account(char *s) +static int __init setup_swap_account(char *s) { - if (!strcmp(s, "1")) - really_do_swap_account = 1; - else if (!strcmp(s, "0")) - really_do_swap_account = 0; + bool res; + + if (!kstrtobool(s, &res) && !res) + pr_warn_once("The swapaccount=0 commandline option is deprecated " + "in favor of configuring swap control via cgroupfs. " + "Please report your usecase to linux-mm@kvack.org if you " + "depend on this functionality.\n"); return 1; } -__setup("swapaccount=", enable_swap_account); +__setup("swapaccount=", setup_swap_account); static u64 swap_current_read(struct cgroup_subsys_state *css, struct cftype *cft) @@ -6599,17 +5307,49 @@ static u64 swap_current_read(struct cgroup_subsys_state *css, return (u64)page_counter_read(&memcg->swap) * PAGE_SIZE; } -static int swap_max_show(struct seq_file *m, void *v) +static int swap_peak_show(struct seq_file *sf, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - unsigned long max = READ_ONCE(memcg->swap.max); + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(sf)); - if (max == PAGE_COUNTER_MAX) - seq_puts(m, "max\n"); - else - seq_printf(m, "%llu\n", (u64)max * PAGE_SIZE); + return peak_show(sf, v, &memcg->swap); +} - return 0; +static ssize_t swap_peak_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + + return peak_write(of, buf, nbytes, off, &memcg->swap, + &memcg->swap_peaks); +} + +static int swap_high_show(struct seq_file *m, void *v) +{ + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->swap.high)); +} + +static ssize_t swap_high_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long high; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "max", &high); + if (err) + return err; + + page_counter_set_high(&memcg->swap, high); + + return nbytes; +} + +static int swap_max_show(struct seq_file *m, void *v) +{ + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->swap.max)); } static ssize_t swap_max_write(struct kernfs_open_file *of, @@ -6631,8 +5371,10 @@ static ssize_t swap_max_write(struct kernfs_open_file *of, static int swap_events_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + seq_printf(m, "high %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_SWAP_HIGH])); seq_printf(m, "max %lu\n", atomic_long_read(&memcg->memory_events[MEMCG_SWAP_MAX])); seq_printf(m, "fail %lu\n", @@ -6648,12 +5390,26 @@ static struct cftype swap_files[] = { .read_u64 = swap_current_read, }, { + .name = "swap.high", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = swap_high_show, + .write = swap_high_write, + }, + { .name = "swap.max", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = swap_max_show, .write = swap_max_write, }, { + .name = "swap.peak", + .flags = CFTYPE_NOT_ON_ROOT, + .open = peak_open, + .release = peak_release, + .seq_show = swap_peak_show, + .write = swap_peak_write, + }, + { .name = "swap.events", .flags = CFTYPE_NOT_ON_ROOT, .file_offset = offsetof(struct mem_cgroup, swap_events_file), @@ -6662,44 +5418,226 @@ static struct cftype swap_files[] = { { } /* terminate */ }; -static struct cftype memsw_cgroup_files[] = { - { - .name = "memsw.usage_in_bytes", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), - .read_u64 = mem_cgroup_read_u64, - }, +#ifdef CONFIG_ZSWAP +/** + * obj_cgroup_may_zswap - check if this cgroup can zswap + * @objcg: the object cgroup + * + * Check if the hierarchical zswap limit has been reached. + * + * This doesn't check for specific headroom, and it is not atomic + * either. But with zswap, the size of the allocation is only known + * once compression has occurred, and this optimistic pre-check avoids + * spending cycles on compression when there is already no room left + * or zswap is disabled altogether somewhere in the hierarchy. + */ +bool obj_cgroup_may_zswap(struct obj_cgroup *objcg) +{ + struct mem_cgroup *memcg, *original_memcg; + bool ret = true; + + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return true; + + original_memcg = get_mem_cgroup_from_objcg(objcg); + for (memcg = original_memcg; !mem_cgroup_is_root(memcg); + memcg = parent_mem_cgroup(memcg)) { + unsigned long max = READ_ONCE(memcg->zswap_max); + unsigned long pages; + + if (max == PAGE_COUNTER_MAX) + continue; + if (max == 0) { + ret = false; + break; + } + + /* Force flush to get accurate stats for charging */ + __mem_cgroup_flush_stats(memcg, true); + pages = memcg_page_state(memcg, MEMCG_ZSWAP_B) / PAGE_SIZE; + if (pages < max) + continue; + ret = false; + break; + } + mem_cgroup_put(original_memcg); + return ret; +} + +/** + * obj_cgroup_charge_zswap - charge compression backend memory + * @objcg: the object cgroup + * @size: size of compressed object + * + * This forces the charge after obj_cgroup_may_zswap() allowed + * compression and storage in zswap for this cgroup to go ahead. + */ +void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size) +{ + struct mem_cgroup *memcg; + + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return; + + VM_WARN_ON_ONCE(!(current->flags & PF_MEMALLOC)); + + /* PF_MEMALLOC context, charging must succeed */ + if (obj_cgroup_charge(objcg, GFP_KERNEL, size)) + VM_WARN_ON_ONCE(1); + + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + mod_memcg_state(memcg, MEMCG_ZSWAP_B, size); + mod_memcg_state(memcg, MEMCG_ZSWAPPED, 1); + rcu_read_unlock(); +} + +/** + * obj_cgroup_uncharge_zswap - uncharge compression backend memory + * @objcg: the object cgroup + * @size: size of compressed object + * + * Uncharges zswap memory on page in. + */ +void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size) +{ + struct mem_cgroup *memcg; + + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return; + + obj_cgroup_uncharge(objcg, size); + + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + mod_memcg_state(memcg, MEMCG_ZSWAP_B, -size); + mod_memcg_state(memcg, MEMCG_ZSWAPPED, -1); + rcu_read_unlock(); +} + +bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg) +{ + /* if zswap is disabled, do not block pages going to the swapping device */ + if (!zswap_is_enabled()) + return true; + + for (; memcg; memcg = parent_mem_cgroup(memcg)) + if (!READ_ONCE(memcg->zswap_writeback)) + return false; + + return true; +} + +static u64 zswap_current_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + mem_cgroup_flush_stats(memcg); + return memcg_page_state(memcg, MEMCG_ZSWAP_B); +} + +static int zswap_max_show(struct seq_file *m, void *v) +{ + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->zswap_max)); +} + +static ssize_t zswap_max_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long max; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "max", &max); + if (err) + return err; + + xchg(&memcg->zswap_max, max); + + return nbytes; +} + +static int zswap_writeback_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + + seq_printf(m, "%d\n", READ_ONCE(memcg->zswap_writeback)); + return 0; +} + +static ssize_t zswap_writeback_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + int zswap_writeback; + ssize_t parse_ret = kstrtoint(strstrip(buf), 0, &zswap_writeback); + + if (parse_ret) + return parse_ret; + + if (zswap_writeback != 0 && zswap_writeback != 1) + return -EINVAL; + + WRITE_ONCE(memcg->zswap_writeback, zswap_writeback); + return nbytes; +} + +static struct cftype zswap_files[] = { { - .name = "memsw.max_usage_in_bytes", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), - .write = mem_cgroup_reset, - .read_u64 = mem_cgroup_read_u64, + .name = "zswap.current", + .flags = CFTYPE_NOT_ON_ROOT, + .read_u64 = zswap_current_read, }, { - .name = "memsw.limit_in_bytes", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), - .write = mem_cgroup_write, - .read_u64 = mem_cgroup_read_u64, + .name = "zswap.max", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = zswap_max_show, + .write = zswap_max_write, }, { - .name = "memsw.failcnt", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), - .write = mem_cgroup_reset, - .read_u64 = mem_cgroup_read_u64, + .name = "zswap.writeback", + .seq_show = zswap_writeback_show, + .write = zswap_writeback_write, }, - { }, /* terminate */ + { } /* terminate */ }; +#endif /* CONFIG_ZSWAP */ static int __init mem_cgroup_swap_init(void) { - if (!mem_cgroup_disabled() && really_do_swap_account) { - do_swap_account = 1; - WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, - swap_files)); - WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, - memsw_cgroup_files)); - } + if (mem_cgroup_disabled()) + return 0; + + WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, swap_files)); +#ifdef CONFIG_MEMCG_V1 + WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, memsw_files)); +#endif +#ifdef CONFIG_ZSWAP + WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, zswap_files)); +#endif return 0; } subsys_initcall(mem_cgroup_swap_init); -#endif /* CONFIG_MEMCG_SWAP */ +#endif /* CONFIG_SWAP */ + +bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid) +{ + return memcg ? cpuset_node_allowed(memcg->css.cgroup, nid) : true; +} + +void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg) +{ + if (mem_cgroup_disabled() || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return; + + if (!memcg) + memcg = root_mem_cgroup; + + pr_warn("Memory cgroup min protection %lukB -- low protection %lukB", + K(atomic_long_read(&memcg->memory.children_min_usage)*PAGE_SIZE), + K(atomic_long_read(&memcg->memory.children_low_usage)*PAGE_SIZE)); +} |