diff options
Diffstat (limited to 'mm/memcontrol.c')
| -rw-r--r-- | mm/memcontrol.c | 2389 |
1 files changed, 942 insertions, 1447 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5177c6d4a2dd..ec4dcf1b9562 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -80,7 +80,7 @@ int do_swap_account __read_mostly; #ifdef CONFIG_MEMCG_SWAP_ENABLED static int really_do_swap_account __initdata = 1; #else -static int really_do_swap_account __initdata = 0; +static int really_do_swap_account __initdata; #endif #else @@ -357,10 +357,9 @@ struct mem_cgroup { struct cg_proto tcp_mem; #endif #if defined(CONFIG_MEMCG_KMEM) - /* analogous to slab_common's slab_caches list. per-memcg */ + /* analogous to slab_common's slab_caches list, but per-memcg; + * protected by memcg_slab_mutex */ struct list_head memcg_slab_caches; - /* Not a spinlock, we can take a lot of time walking the list */ - struct mutex slab_caches_mutex; /* Index in the kmem_cache->memcg_params->memcg_caches array */ int kmemcg_id; #endif @@ -527,18 +526,14 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { - /* - * The ID of the root cgroup is 0, but memcg treat 0 as an - * invalid ID, so we return (cgroup_id + 1). - */ - return memcg->css.cgroup->id + 1; + return memcg->css.id; } static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) { struct cgroup_subsys_state *css; - css = css_from_id(id - 1, &memory_cgrp_subsys); + css = css_from_id(id, &memory_cgrp_subsys); return mem_cgroup_from_css(css); } @@ -571,7 +566,8 @@ void sock_update_memcg(struct sock *sk) memcg = mem_cgroup_from_task(current); cg_proto = sk->sk_prot->proto_cgroup(memcg); if (!mem_cgroup_is_root(memcg) && - memcg_proto_active(cg_proto) && css_tryget(&memcg->css)) { + memcg_proto_active(cg_proto) && + css_tryget_online(&memcg->css)) { sk->sk_cgrp = cg_proto; } rcu_read_unlock(); @@ -677,9 +673,11 @@ static void disarm_static_keys(struct mem_cgroup *memcg) static void drain_all_stock_async(struct mem_cgroup *memcg); static struct mem_cgroup_per_zone * -mem_cgroup_zoneinfo(struct mem_cgroup *memcg, int nid, int zid) +mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) { - VM_BUG_ON((unsigned)nid >= nr_node_ids); + int nid = zone_to_nid(zone); + int zid = zone_idx(zone); + return &memcg->nodeinfo[nid]->zoneinfo[zid]; } @@ -689,12 +687,12 @@ struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg) } static struct mem_cgroup_per_zone * -page_cgroup_zoneinfo(struct mem_cgroup *memcg, struct page *page) +mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page) { int nid = page_to_nid(page); int zid = page_zonenum(page); - return mem_cgroup_zoneinfo(memcg, nid, zid); + return &memcg->nodeinfo[nid]->zoneinfo[zid]; } static struct mem_cgroup_tree_per_zone * @@ -712,11 +710,9 @@ soft_limit_tree_from_page(struct page *page) return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; } -static void -__mem_cgroup_insert_exceeded(struct mem_cgroup *memcg, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz, - unsigned long long new_usage_in_excess) +static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz, + unsigned long long new_usage_in_excess) { struct rb_node **p = &mctz->rb_root.rb_node; struct rb_node *parent = NULL; @@ -746,10 +742,8 @@ __mem_cgroup_insert_exceeded(struct mem_cgroup *memcg, mz->on_tree = true; } -static void -__mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) +static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) { if (!mz->on_tree) return; @@ -757,14 +751,14 @@ __mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, mz->on_tree = false; } -static void -mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) +static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) { - spin_lock(&mctz->lock); - __mem_cgroup_remove_exceeded(memcg, mz, mctz); - spin_unlock(&mctz->lock); + unsigned long flags; + + spin_lock_irqsave(&mctz->lock, flags); + __mem_cgroup_remove_exceeded(mz, mctz); + spin_unlock_irqrestore(&mctz->lock, flags); } @@ -773,47 +767,47 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) unsigned long long excess; struct mem_cgroup_per_zone *mz; struct mem_cgroup_tree_per_zone *mctz; - int nid = page_to_nid(page); - int zid = page_zonenum(page); - mctz = soft_limit_tree_from_page(page); + mctz = soft_limit_tree_from_page(page); /* * 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_zoneinfo(memcg, nid, zid); + mz = mem_cgroup_page_zoneinfo(memcg, page); excess = res_counter_soft_limit_excess(&memcg->res); /* * We have to update the tree if mz is on RB-tree or * mem is over its softlimit. */ if (excess || mz->on_tree) { - spin_lock(&mctz->lock); + unsigned long flags; + + spin_lock_irqsave(&mctz->lock, flags); /* if on-tree, remove it */ if (mz->on_tree) - __mem_cgroup_remove_exceeded(memcg, mz, mctz); + __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(memcg, mz, mctz, excess); - spin_unlock(&mctz->lock); + __mem_cgroup_insert_exceeded(mz, mctz, excess); + spin_unlock_irqrestore(&mctz->lock, flags); } } } static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) { - int node, zone; - struct mem_cgroup_per_zone *mz; struct mem_cgroup_tree_per_zone *mctz; + struct mem_cgroup_per_zone *mz; + int nid, zid; - for_each_node(node) { - for (zone = 0; zone < MAX_NR_ZONES; zone++) { - mz = mem_cgroup_zoneinfo(memcg, node, zone); - mctz = soft_limit_tree_node_zone(node, zone); - mem_cgroup_remove_exceeded(memcg, mz, mctz); + for_each_node(nid) { + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; + mctz = soft_limit_tree_node_zone(nid, zid); + mem_cgroup_remove_exceeded(mz, mctz); } } } @@ -836,9 +830,9 @@ retry: * we will to add it back at the end of reclaim to its correct * position in the tree. */ - __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz); + __mem_cgroup_remove_exceeded(mz, mctz); if (!res_counter_soft_limit_excess(&mz->memcg->res) || - !css_tryget(&mz->memcg->css)) + !css_tryget_online(&mz->memcg->css)) goto retry; done: return mz; @@ -849,9 +843,9 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) { struct mem_cgroup_per_zone *mz; - spin_lock(&mctz->lock); + spin_lock_irq(&mctz->lock); mz = __mem_cgroup_largest_soft_limit_node(mctz); - spin_unlock(&mctz->lock); + spin_unlock_irq(&mctz->lock); return mz; } @@ -892,13 +886,6 @@ static long mem_cgroup_read_stat(struct mem_cgroup *memcg, return val; } -static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg, - bool charge) -{ - int val = (charge) ? 1 : -1; - this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAP], val); -} - static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, enum mem_cgroup_events_index idx) { @@ -919,13 +906,13 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, struct page *page, - bool anon, int nr_pages) + int nr_pages) { /* * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is * counted as CACHE even if it's on ANON LRU. */ - if (anon) + if (PageAnon(page)) __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS], nr_pages); else @@ -947,8 +934,7 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, __this_cpu_add(memcg->stat->nr_page_events, nr_pages); } -unsigned long -mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) +unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { struct mem_cgroup_per_zone *mz; @@ -956,46 +942,38 @@ mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) return mz->lru_size[lru]; } -static unsigned long -mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid, - unsigned int lru_mask) -{ - struct mem_cgroup_per_zone *mz; - enum lru_list lru; - unsigned long ret = 0; - - mz = mem_cgroup_zoneinfo(memcg, nid, zid); - - for_each_lru(lru) { - if (BIT(lru) & lru_mask) - ret += mz->lru_size[lru]; - } - return ret; -} - -static unsigned long -mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, - int nid, unsigned int lru_mask) +static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, + int nid, + unsigned int lru_mask) { - u64 total = 0; + unsigned long nr = 0; int zid; - for (zid = 0; zid < MAX_NR_ZONES; zid++) - total += mem_cgroup_zone_nr_lru_pages(memcg, - nid, zid, lru_mask); + VM_BUG_ON((unsigned)nid >= nr_node_ids); - return total; + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + struct mem_cgroup_per_zone *mz; + enum lru_list lru; + + for_each_lru(lru) { + if (!(BIT(lru) & lru_mask)) + continue; + mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; + nr += mz->lru_size[lru]; + } + } + return nr; } static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg, unsigned int lru_mask) { + unsigned long nr = 0; int nid; - u64 total = 0; for_each_node_state(nid, N_MEMORY) - total += mem_cgroup_node_nr_lru_pages(memcg, nid, lru_mask); - return total; + nr += mem_cgroup_node_nr_lru_pages(memcg, nid, lru_mask); + return nr; } static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, @@ -1032,7 +1010,6 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, */ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) { - preempt_disable(); /* threshold event is triggered in finer grain than soft limit */ if (unlikely(mem_cgroup_event_ratelimit(memcg, MEM_CGROUP_TARGET_THRESH))) { @@ -1045,8 +1022,6 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) do_numainfo = mem_cgroup_event_ratelimit(memcg, MEM_CGROUP_TARGET_NUMAINFO); #endif - preempt_enable(); - mem_cgroup_threshold(memcg); if (unlikely(do_softlimit)) mem_cgroup_update_tree(memcg, page); @@ -1054,8 +1029,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) if (unlikely(do_numainfo)) atomic_inc(&memcg->numainfo_events); #endif - } else - preempt_enable(); + } } struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) @@ -1089,7 +1063,7 @@ static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) if (unlikely(!memcg)) memcg = root_mem_cgroup; } - } while (!css_tryget(&memcg->css)); + } while (!css_tryget_online(&memcg->css)); rcu_read_unlock(); return memcg; } @@ -1126,7 +1100,8 @@ skip_node: */ if (next_css) { if ((next_css == &root->css) || - ((next_css->flags & CSS_ONLINE) && css_tryget(next_css))) + ((next_css->flags & CSS_ONLINE) && + css_tryget_online(next_css))) return mem_cgroup_from_css(next_css); prev_css = next_css; @@ -1172,7 +1147,7 @@ mem_cgroup_iter_load(struct mem_cgroup_reclaim_iter *iter, * would be returned all the time. */ if (position && position != root && - !css_tryget(&position->css)) + !css_tryget_online(&position->css)) position = NULL; } return position; @@ -1243,11 +1218,9 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, int uninitialized_var(seq); if (reclaim) { - int nid = zone_to_nid(reclaim->zone); - int zid = zone_idx(reclaim->zone); struct mem_cgroup_per_zone *mz; - mz = mem_cgroup_zoneinfo(root, nid, zid); + mz = mem_cgroup_zone_zoneinfo(root, reclaim->zone); iter = &mz->reclaim_iter[reclaim->priority]; if (prev && reclaim->generation != iter->generation) { iter->last_visited = NULL; @@ -1354,7 +1327,7 @@ struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, goto out; } - mz = mem_cgroup_zoneinfo(memcg, zone_to_nid(zone), zone_idx(zone)); + mz = mem_cgroup_zone_zoneinfo(memcg, zone); lruvec = &mz->lruvec; out: /* @@ -1367,20 +1340,6 @@ out: return lruvec; } -/* - * Following LRU functions are allowed to be used without PCG_LOCK. - * Operations are called by routine of global LRU independently from memcg. - * What we have to take care of here is validness of pc->mem_cgroup. - * - * Changes to pc->mem_cgroup happens when - * 1. charge - * 2. moving account - * In typical case, "charge" is done before add-to-lru. Exception is SwapCache. - * It is added to LRU before charge. - * If PCG_USED bit is not set, page_cgroup is not added to this private LRU. - * When moving account, the page is not on LRU. It's isolated. - */ - /** * mem_cgroup_page_lruvec - return lruvec for adding an lru page * @page: the page @@ -1413,7 +1372,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone) if (!PageLRU(page) && !PageCgroupUsed(pc) && memcg != root_mem_cgroup) pc->mem_cgroup = memcg = root_mem_cgroup; - mz = page_cgroup_zoneinfo(memcg, page); + mz = mem_cgroup_page_zoneinfo(memcg, page); lruvec = &mz->lruvec; out: /* @@ -1551,7 +1510,7 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* root ? */ - if (!css_parent(&memcg->css)) + if (mem_cgroup_disabled() || !memcg->css.parent) return vm_swappiness; return memcg->swappiness; @@ -1595,23 +1554,12 @@ static void mem_cgroup_end_move(struct mem_cgroup *memcg) } /* - * 2 routines for checking "mem" is under move_account() or not. + * A routine for checking "mem" is under move_account() or not. * - * mem_cgroup_stolen() - checking whether a cgroup is mc.from or not. This - * is used for avoiding races in accounting. If true, - * pc->mem_cgroup may be overwritten. - * - * mem_cgroup_under_move() - checking a cgroup is mc.from or mc.to or - * under hierarchy of moving cgroups. This is for - * waiting at hith-memory prressure caused by "move". + * 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_stolen(struct mem_cgroup *memcg) -{ - VM_BUG_ON(!rcu_read_lock_held()); - return atomic_read(&memcg->moving_account) > 0; -} - static bool mem_cgroup_under_move(struct mem_cgroup *memcg) { struct mem_cgroup *from; @@ -1654,7 +1602,6 @@ static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg) * Take this lock when * - a code tries to modify page's memcg while it's USED. * - a code tries to modify page state accounting in a memcg. - * see mem_cgroup_stolen(), too. */ static void move_lock_mem_cgroup(struct mem_cgroup *memcg, unsigned long *flags) @@ -2289,27 +2236,18 @@ cleanup: } /* - * Currently used to update mapped file statistics, but the routine can be - * generalized to update other statistics as well. + * Used to update mapped file or writeback or other statistics. * * Notes: Race condition * - * We usually use page_cgroup_lock() for accessing page_cgroup member but - * it tends to be costly. But considering some conditions, we doesn't need - * to do so _always_. - * - * Considering "charge", lock_page_cgroup() is not required because all - * file-stat operations happen after a page is attached to radix-tree. There - * are no race with "charge". + * Charging occurs during page instantiation, while the page is + * unmapped and locked in page migration, or while the page table is + * locked in THP migration. No race is possible. * - * Considering "uncharge", we know that memcg doesn't clear pc->mem_cgroup - * at "uncharge" intentionally. So, we always see valid pc->mem_cgroup even - * if there are race with "uncharge". Statistics itself is properly handled - * by flags. + * Uncharge happens to pages with zero references, no race possible. * - * Considering "move", this is an only case we see a race. To make the race - * small, we check mm->moving_account and detect there are possibility of race - * If there is, we take a lock. + * Charge moving between groups is protected by checking mm->moving + * account and taking the move_lock in the slowpath. */ void __mem_cgroup_begin_update_page_stat(struct page *page, @@ -2327,9 +2265,10 @@ again: * If this memory cgroup is not under account moving, we don't * need to take move_lock_mem_cgroup(). Because we already hold * rcu_read_lock(), any calls to move_account will be delayed until - * rcu_read_unlock() if mem_cgroup_stolen() == true. + * rcu_read_unlock(). */ - if (!mem_cgroup_stolen(memcg)) + VM_BUG_ON(!rcu_read_lock_held()); + if (atomic_read(&memcg->moving_account) <= 0) return; move_lock_mem_cgroup(memcg, flags); @@ -2437,7 +2376,7 @@ static void drain_stock(struct memcg_stock_pcp *stock) */ static void drain_local_stock(struct work_struct *dummy) { - struct memcg_stock_pcp *stock = &__get_cpu_var(memcg_stock); + struct memcg_stock_pcp *stock = this_cpu_ptr(&memcg_stock); drain_stock(stock); clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); } @@ -2583,55 +2522,63 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb, return NOTIFY_OK; } - -/* See mem_cgroup_try_charge() for details */ -enum { - CHARGE_OK, /* success */ - CHARGE_RETRY, /* need to retry but retry is not bad */ - CHARGE_NOMEM, /* we can't do more. return -ENOMEM */ - CHARGE_WOULDBLOCK, /* GFP_WAIT wasn't set and no enough res. */ -}; - -static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, - unsigned int nr_pages, unsigned int min_pages, - bool invoke_oom) +static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, + unsigned int nr_pages) { - unsigned long csize = nr_pages * PAGE_SIZE; + unsigned int batch = max(CHARGE_BATCH, nr_pages); + int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; struct mem_cgroup *mem_over_limit; struct res_counter *fail_res; + unsigned long nr_reclaimed; unsigned long flags = 0; - int ret; + unsigned long long size; + int ret = 0; - ret = res_counter_charge(&memcg->res, csize, &fail_res); +retry: + if (consume_stock(memcg, nr_pages)) + goto done; - if (likely(!ret)) { + size = batch * PAGE_SIZE; + if (!res_counter_charge(&memcg->res, size, &fail_res)) { if (!do_swap_account) - return CHARGE_OK; - ret = res_counter_charge(&memcg->memsw, csize, &fail_res); - if (likely(!ret)) - return CHARGE_OK; - - res_counter_uncharge(&memcg->res, csize); + goto done_restock; + if (!res_counter_charge(&memcg->memsw, size, &fail_res)) + goto done_restock; + res_counter_uncharge(&memcg->res, size); mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw); flags |= MEM_CGROUP_RECLAIM_NOSWAP; } else mem_over_limit = mem_cgroup_from_res_counter(fail_res, res); + + if (batch > nr_pages) { + batch = nr_pages; + goto retry; + } + /* - * Never reclaim on behalf of optional batching, retry with a - * single page instead. + * 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 (nr_pages > min_pages) - return CHARGE_RETRY; + if (unlikely(test_thread_flag(TIF_MEMDIE) || + fatal_signal_pending(current) || + current->flags & PF_EXITING)) + goto bypass; + + if (unlikely(task_in_memcg_oom(current))) + goto nomem; if (!(gfp_mask & __GFP_WAIT)) - return CHARGE_WOULDBLOCK; + goto nomem; - if (gfp_mask & __GFP_NORETRY) - return CHARGE_NOMEM; + nr_reclaimed = mem_cgroup_reclaim(mem_over_limit, gfp_mask, flags); - ret = mem_cgroup_reclaim(mem_over_limit, gfp_mask, flags); if (mem_cgroup_margin(mem_over_limit) >= nr_pages) - return CHARGE_RETRY; + goto retry; + + if (gfp_mask & __GFP_NORETRY) + goto nomem; /* * Even though the limit is exceeded at this point, reclaim * may have been able to free some pages. Retry the charge @@ -2641,141 +2588,47 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, * unlikely to succeed so close to the limit, and we fall back * to regular pages anyway in case of failure. */ - if (nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER) && ret) - return CHARGE_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)) - return CHARGE_RETRY; - - if (invoke_oom) - mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(csize)); - - return CHARGE_NOMEM; -} - -/** - * mem_cgroup_try_charge - try charging a memcg - * @memcg: memcg to charge - * @nr_pages: number of pages to charge - * @oom: trigger OOM if reclaim fails - * - * Returns 0 if @memcg was charged successfully, -EINTR if the charge - * was bypassed to root_mem_cgroup, and -ENOMEM if the charge failed. - */ -static int mem_cgroup_try_charge(struct mem_cgroup *memcg, - gfp_t gfp_mask, - unsigned int nr_pages, - bool oom) -{ - unsigned int batch = max(CHARGE_BATCH, nr_pages); - int nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES; - int ret; - - if (mem_cgroup_is_root(memcg)) - goto done; - /* - * 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(test_thread_flag(TIF_MEMDIE) || - fatal_signal_pending(current))) - goto bypass; + goto retry; - if (unlikely(task_in_memcg_oom(current))) - goto nomem; + if (nr_retries--) + goto retry; if (gfp_mask & __GFP_NOFAIL) - oom = false; -again: - if (consume_stock(memcg, nr_pages)) - goto done; - - do { - bool invoke_oom = oom && !nr_oom_retries; - - /* If killed, bypass charge */ - if (fatal_signal_pending(current)) - goto bypass; + goto bypass; - ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, - nr_pages, invoke_oom); - switch (ret) { - case CHARGE_OK: - break; - case CHARGE_RETRY: /* not in OOM situation but retry */ - batch = nr_pages; - goto again; - case CHARGE_WOULDBLOCK: /* !__GFP_WAIT */ - goto nomem; - case CHARGE_NOMEM: /* OOM routine works */ - if (!oom || invoke_oom) - goto nomem; - nr_oom_retries--; - break; - } - } while (ret != CHARGE_OK); + if (fatal_signal_pending(current)) + goto bypass; - if (batch > nr_pages) - refill_stock(memcg, batch - nr_pages); -done: - return 0; + mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(nr_pages)); nomem: if (!(gfp_mask & __GFP_NOFAIL)) return -ENOMEM; bypass: - return -EINTR; -} + memcg = root_mem_cgroup; + ret = -EINTR; + goto retry; -/** - * mem_cgroup_try_charge_mm - try charging a mm - * @mm: mm_struct to charge - * @nr_pages: number of pages to charge - * @oom: trigger OOM if reclaim fails - * - * Returns the charged mem_cgroup associated with the given mm_struct or - * NULL the charge failed. - */ -static struct mem_cgroup *mem_cgroup_try_charge_mm(struct mm_struct *mm, - gfp_t gfp_mask, - unsigned int nr_pages, - bool oom) - -{ - struct mem_cgroup *memcg; - int ret; - - memcg = get_mem_cgroup_from_mm(mm); - ret = mem_cgroup_try_charge(memcg, gfp_mask, nr_pages, oom); - css_put(&memcg->css); - if (ret == -EINTR) - memcg = root_mem_cgroup; - else if (ret) - memcg = NULL; - - return memcg; +done_restock: + if (batch > nr_pages) + refill_stock(memcg, batch - nr_pages); +done: + return ret; } -/* - * Somemtimes we have to undo a charge we got by try_charge(). - * This function is for that and do uncharge, put css's refcnt. - * gotten by try_charge(). - */ -static void __mem_cgroup_cancel_charge(struct mem_cgroup *memcg, - unsigned int nr_pages) +static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) { - if (!mem_cgroup_is_root(memcg)) { - unsigned long bytes = nr_pages * PAGE_SIZE; + unsigned long bytes = nr_pages * PAGE_SIZE; - res_counter_uncharge(&memcg->res, bytes); - if (do_swap_account) - res_counter_uncharge(&memcg->memsw, bytes); - } + res_counter_uncharge(&memcg->res, bytes); + if (do_swap_account) + res_counter_uncharge(&memcg->memsw, bytes); } /* @@ -2787,9 +2640,6 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg, { unsigned long bytes = nr_pages * PAGE_SIZE; - if (mem_cgroup_is_root(memcg)) - return; - res_counter_uncharge_until(&memcg->res, memcg->res.parent, bytes); if (do_swap_account) res_counter_uncharge_until(&memcg->memsw, @@ -2798,9 +2648,9 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg, /* * A helper function to get mem_cgroup from ID. must be called under - * rcu_read_lock(). The caller is responsible for calling css_tryget if - * the mem_cgroup is used for charging. (dropping refcnt from swap can be - * called against removed memcg.) + * rcu_read_lock(). The caller is responsible for calling + * css_tryget_online() if the mem_cgroup is used for charging. (dropping + * refcnt from swap can be called against removed memcg.) */ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) { @@ -2810,6 +2660,16 @@ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) return mem_cgroup_from_id(id); } +/* + * try_get_mem_cgroup_from_page - look up page's memcg association + * @page: the page + * + * Look up, get a css reference, and return the memcg that owns @page. + * + * The page must be locked to prevent racing with swap-in and page + * cache charges. If coming from an unlocked page table, the caller + * must ensure the page is on the LRU or this can race with charging. + */ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) { struct mem_cgroup *memcg = NULL; @@ -2820,37 +2680,59 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) VM_BUG_ON_PAGE(!PageLocked(page), page); pc = lookup_page_cgroup(page); - lock_page_cgroup(pc); if (PageCgroupUsed(pc)) { memcg = pc->mem_cgroup; - if (memcg && !css_tryget(&memcg->css)) + if (memcg && !css_tryget_online(&memcg->css)) memcg = NULL; } else if (PageSwapCache(page)) { ent.val = page_private(page); id = lookup_swap_cgroup_id(ent); rcu_read_lock(); memcg = mem_cgroup_lookup(id); - if (memcg && !css_tryget(&memcg->css)) + if (memcg && !css_tryget_online(&memcg->css)) memcg = NULL; rcu_read_unlock(); } - unlock_page_cgroup(pc); return memcg; } -static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, - struct page *page, - unsigned int nr_pages, - enum charge_type ctype, - bool lrucare) +static void lock_page_lru(struct page *page, int *isolated) +{ + struct zone *zone = page_zone(page); + + spin_lock_irq(&zone->lru_lock); + if (PageLRU(page)) { + struct lruvec *lruvec; + + lruvec = mem_cgroup_page_lruvec(page, zone); + 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; + + lruvec = mem_cgroup_page_lruvec(page, zone); + 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); +} + +static void commit_charge(struct page *page, struct mem_cgroup *memcg, + bool lrucare) { struct page_cgroup *pc = lookup_page_cgroup(page); - struct zone *uninitialized_var(zone); - struct lruvec *lruvec; - bool was_on_lru = false; - bool anon; + int isolated; - lock_page_cgroup(pc); VM_BUG_ON_PAGE(PageCgroupUsed(pc), page); /* * we don't need page_cgroup_lock about tail pages, becase they are not @@ -2861,57 +2743,39 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, * 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) { - zone = page_zone(page); - spin_lock_irq(&zone->lru_lock); - if (PageLRU(page)) { - lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup); - ClearPageLRU(page); - del_page_from_lru_list(page, lruvec, page_lru(page)); - was_on_lru = true; - } - } + if (lrucare) + lock_page_lru(page, &isolated); - pc->mem_cgroup = memcg; /* - * We access a page_cgroup asynchronously without lock_page_cgroup(). - * Especially when a page_cgroup is taken from a page, pc->mem_cgroup - * is accessed after testing USED bit. To make pc->mem_cgroup visible - * before USED bit, we need memory barrier here. - * See mem_cgroup_add_lru_list(), etc. + * Nobody should be changing or seriously looking at + * pc->mem_cgroup and pc->flags 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 + * + * - a page cache insertion, a swapin fault, or a migration + * have the page locked */ - smp_wmb(); - SetPageCgroupUsed(pc); - - if (lrucare) { - if (was_on_lru) { - lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup); - 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); - } - - if (ctype == MEM_CGROUP_CHARGE_TYPE_ANON) - anon = true; - else - anon = false; - - mem_cgroup_charge_statistics(memcg, page, anon, nr_pages); - unlock_page_cgroup(pc); + pc->mem_cgroup = memcg; + pc->flags = PCG_USED | PCG_MEM | (do_swap_account ? PCG_MEMSW : 0); - /* - * "charge_statistics" updated event counter. Then, check it. - * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree. - * if they exceeds softlimit. - */ - memcg_check_events(memcg, page); + if (lrucare) + unlock_page_lru(page, isolated); } static DEFINE_MUTEX(set_limit_mutex); #ifdef CONFIG_MEMCG_KMEM +/* + * The memcg_slab_mutex is held whenever a per memcg kmem cache is created or + * destroyed. It protects memcg_caches arrays and memcg_slab_caches lists. + */ +static DEFINE_MUTEX(memcg_slab_mutex); + static DEFINE_MUTEX(activate_kmem_mutex); static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg) @@ -2944,10 +2808,10 @@ static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v) print_slabinfo_header(m); - mutex_lock(&memcg->slab_caches_mutex); + mutex_lock(&memcg_slab_mutex); list_for_each_entry(params, &memcg->memcg_slab_caches, list) cache_show(memcg_params_to_cache(params), m); - mutex_unlock(&memcg->slab_caches_mutex); + mutex_unlock(&memcg_slab_mutex); return 0; } @@ -2962,22 +2826,21 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size) if (ret) return ret; - ret = mem_cgroup_try_charge(memcg, gfp, size >> PAGE_SHIFT, - oom_gfp_allowed(gfp)); + ret = try_charge(memcg, gfp, size >> PAGE_SHIFT); if (ret == -EINTR) { /* - * mem_cgroup_try_charge() chosed to bypass to root due to - * OOM kill or fatal signal. Since our only options are to - * either fail the allocation or charge it to this cgroup, do - * it as a temporary condition. But we can't fail. From a - * kmem/slab perspective, the cache has already been selected, - * by mem_cgroup_kmem_get_cache(), so it is too late to change + * try_charge() chose to bypass to root due to OOM kill or + * fatal signal. Since our only options are to either fail + * the allocation or charge it to this cgroup, do it as a + * temporary condition. But we can't fail. From a kmem/slab + * perspective, the cache has already been selected, by + * mem_cgroup_kmem_get_cache(), so it is too late to change * our minds. * * This condition will only trigger if the task entered - * memcg_charge_kmem in a sane state, but was OOM-killed during - * mem_cgroup_try_charge() above. Tasks that were already - * dying when the allocation triggers should have been already + * memcg_charge_kmem in a sane state, but was OOM-killed + * during try_charge() above. Tasks that were already dying + * when the allocation triggers should have been already * directed to the root cgroup in memcontrol.h */ res_counter_charge_nofail(&memcg->res, size, &fail_res); @@ -3049,8 +2912,6 @@ void memcg_update_array_size(int num) memcg_limited_groups_array_size = memcg_caches_array_size(num); } -static void kmem_cache_destroy_work_func(struct work_struct *w); - int memcg_update_cache_size(struct kmem_cache *s, int num_groups) { struct memcg_cache_params *cur_params = s->memcg_params; @@ -3103,29 +2964,6 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups) return 0; } -char *memcg_create_cache_name(struct mem_cgroup *memcg, - struct kmem_cache *root_cache) -{ - static char *buf = NULL; - - /* - * We need a mutex here to protect the shared buffer. Since this is - * expected to be called only on cache creation, we can employ the - * slab_mutex for that purpose. - */ - lockdep_assert_held(&slab_mutex); - - if (!buf) { - buf = kmalloc(NAME_MAX + 1, GFP_KERNEL); - if (!buf) - return NULL; - } - - cgroup_name(memcg->css.cgroup, buf, NAME_MAX + 1); - return kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, - memcg_cache_id(memcg), buf); -} - int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, struct kmem_cache *root_cache) { @@ -3147,8 +2985,6 @@ int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, if (memcg) { s->memcg_params->memcg = memcg; s->memcg_params->root_cache = root_cache; - INIT_WORK(&s->memcg_params->destroy, - kmem_cache_destroy_work_func); css_get(&memcg->css); } else s->memcg_params->is_root_cache = true; @@ -3165,24 +3001,37 @@ void memcg_free_cache_params(struct kmem_cache *s) kfree(s->memcg_params); } -void memcg_register_cache(struct kmem_cache *s) +static void memcg_register_cache(struct mem_cgroup *memcg, + struct kmem_cache *root_cache) { - struct kmem_cache *root; - struct mem_cgroup *memcg; + static char memcg_name_buf[NAME_MAX + 1]; /* protected by + memcg_slab_mutex */ + struct kmem_cache *cachep; int id; - if (is_root_cache(s)) + lockdep_assert_held(&memcg_slab_mutex); + + id = memcg_cache_id(memcg); + + /* + * Since per-memcg caches are created asynchronously on first + * allocation (see memcg_kmem_get_cache()), several threads can try to + * create the same cache, but only one of them may succeed. + */ + if (cache_from_memcg_idx(root_cache, id)) return; + cgroup_name(memcg->css.cgroup, memcg_name_buf, NAME_MAX + 1); + cachep = memcg_create_kmem_cache(memcg, root_cache, memcg_name_buf); /* - * Holding the slab_mutex assures nobody will touch the memcg_caches - * array while we are modifying it. + * If we could not create a memcg cache, do not complain, because + * that's not critical at all as we can always proceed with the root + * cache. */ - lockdep_assert_held(&slab_mutex); + if (!cachep) + return; - root = s->memcg_params->root_cache; - memcg = s->memcg_params->memcg; - id = memcg_cache_id(memcg); + list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches); /* * Since readers won't lock (see cache_from_memcg_idx()), we need a @@ -3191,49 +3040,30 @@ void memcg_register_cache(struct kmem_cache *s) */ smp_wmb(); - /* - * Initialize the pointer to this cache in its parent's memcg_params - * before adding it to the memcg_slab_caches list, otherwise we can - * fail to convert memcg_params_to_cache() while traversing the list. - */ - VM_BUG_ON(root->memcg_params->memcg_caches[id]); - root->memcg_params->memcg_caches[id] = s; - - mutex_lock(&memcg->slab_caches_mutex); - list_add(&s->memcg_params->list, &memcg->memcg_slab_caches); - mutex_unlock(&memcg->slab_caches_mutex); + BUG_ON(root_cache->memcg_params->memcg_caches[id]); + root_cache->memcg_params->memcg_caches[id] = cachep; } -void memcg_unregister_cache(struct kmem_cache *s) +static void memcg_unregister_cache(struct kmem_cache *cachep) { - struct kmem_cache *root; + struct kmem_cache *root_cache; struct mem_cgroup *memcg; int id; - if (is_root_cache(s)) - return; + lockdep_assert_held(&memcg_slab_mutex); - /* - * Holding the slab_mutex assures nobody will touch the memcg_caches - * array while we are modifying it. - */ - lockdep_assert_held(&slab_mutex); + BUG_ON(is_root_cache(cachep)); - root = s->memcg_params->root_cache; - memcg = s->memcg_params->memcg; + root_cache = cachep->memcg_params->root_cache; + memcg = cachep->memcg_params->memcg; id = memcg_cache_id(memcg); - mutex_lock(&memcg->slab_caches_mutex); - list_del(&s->memcg_params->list); - mutex_unlock(&memcg->slab_caches_mutex); + BUG_ON(root_cache->memcg_params->memcg_caches[id] != cachep); + root_cache->memcg_params->memcg_caches[id] = NULL; - /* - * Clear the pointer to this cache in its parent's memcg_params only - * after removing it from the memcg_slab_caches list, otherwise we can - * fail to convert memcg_params_to_cache() while traversing the list. - */ - VM_BUG_ON(root->memcg_params->memcg_caches[id] != s); - root->memcg_params->memcg_caches[id] = NULL; + list_del(&cachep->memcg_params->list); + + kmem_cache_destroy(cachep); } /* @@ -3267,144 +3097,61 @@ static inline void memcg_resume_kmem_account(void) current->memcg_kmem_skip_account--; } -static void kmem_cache_destroy_work_func(struct work_struct *w) -{ - struct kmem_cache *cachep; - struct memcg_cache_params *p; - - p = container_of(w, struct memcg_cache_params, destroy); - - cachep = memcg_params_to_cache(p); - - /* - * If we get down to 0 after shrink, we could delete right away. - * However, memcg_release_pages() already puts us back in the workqueue - * in that case. If we proceed deleting, we'll get a dangling - * reference, and removing the object from the workqueue in that case - * is unnecessary complication. We are not a fast path. - * - * Note that this case is fundamentally different from racing with - * shrink_slab(): if memcg_cgroup_destroy_cache() is called in - * kmem_cache_shrink, not only we would be reinserting a dead cache - * into the queue, but doing so from inside the worker racing to - * destroy it. - * - * So if we aren't down to zero, we'll just schedule a worker and try - * again - */ - if (atomic_read(&cachep->memcg_params->nr_pages) != 0) - kmem_cache_shrink(cachep); - else - kmem_cache_destroy(cachep); -} - -void mem_cgroup_destroy_cache(struct kmem_cache *cachep) -{ - if (!cachep->memcg_params->dead) - return; - - /* - * There are many ways in which we can get here. - * - * We can get to a memory-pressure situation while the delayed work is - * still pending to run. The vmscan shrinkers can then release all - * cache memory and get us to destruction. If this is the case, we'll - * be executed twice, which is a bug (the second time will execute over - * bogus data). In this case, cancelling the work should be fine. - * - * But we can also get here from the worker itself, if - * kmem_cache_shrink is enough to shake all the remaining objects and - * get the page count to 0. In this case, we'll deadlock if we try to - * cancel the work (the worker runs with an internal lock held, which - * is the same lock we would hold for cancel_work_sync().) - * - * Since we can't possibly know who got us here, just refrain from - * running if there is already work pending - */ - if (work_pending(&cachep->memcg_params->destroy)) - return; - /* - * We have to defer the actual destroying to a workqueue, because - * we might currently be in a context that cannot sleep. - */ - schedule_work(&cachep->memcg_params->destroy); -} - -int __kmem_cache_destroy_memcg_children(struct kmem_cache *s) +int __memcg_cleanup_cache_params(struct kmem_cache *s) { struct kmem_cache *c; int i, failed = 0; - /* - * If the cache is being destroyed, we trust that there is no one else - * requesting objects from it. Even if there are, the sanity checks in - * kmem_cache_destroy should caught this ill-case. - * - * Still, we don't want anyone else freeing memcg_caches under our - * noses, which can happen if a new memcg comes to life. As usual, - * we'll take the activate_kmem_mutex to protect ourselves against - * this. - */ - mutex_lock(&activate_kmem_mutex); + mutex_lock(&memcg_slab_mutex); for_each_memcg_cache_index(i) { c = cache_from_memcg_idx(s, i); if (!c) continue; - /* - * We will now manually delete the caches, so to avoid races - * we need to cancel all pending destruction workers and - * proceed with destruction ourselves. - * - * kmem_cache_destroy() will call kmem_cache_shrink internally, - * and that could spawn the workers again: it is likely that - * the cache still have active pages until this very moment. - * This would lead us back to mem_cgroup_destroy_cache. - * - * But that will not execute at all if the "dead" flag is not - * set, so flip it down to guarantee we are in control. - */ - c->memcg_params->dead = false; - cancel_work_sync(&c->memcg_params->destroy); - kmem_cache_destroy(c); + memcg_unregister_cache(c); if (cache_from_memcg_idx(s, i)) failed++; } - mutex_unlock(&activate_kmem_mutex); + mutex_unlock(&memcg_slab_mutex); return failed; } -static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg) +static void memcg_unregister_all_caches(struct mem_cgroup *memcg) { struct kmem_cache *cachep; - struct memcg_cache_params *params; + struct memcg_cache_params *params, *tmp; if (!memcg_kmem_is_active(memcg)) return; - mutex_lock(&memcg->slab_caches_mutex); - list_for_each_entry(params, &memcg->memcg_slab_caches, list) { + mutex_lock(&memcg_slab_mutex); + list_for_each_entry_safe(params, tmp, &memcg->memcg_slab_caches, list) { cachep = memcg_params_to_cache(params); - cachep->memcg_params->dead = true; - schedule_work(&cachep->memcg_params->destroy); + kmem_cache_shrink(cachep); + if (atomic_read(&cachep->memcg_params->nr_pages) == 0) + memcg_unregister_cache(cachep); } - mutex_unlock(&memcg->slab_caches_mutex); + mutex_unlock(&memcg_slab_mutex); } -struct create_work { +struct memcg_register_cache_work { struct mem_cgroup *memcg; struct kmem_cache *cachep; struct work_struct work; }; -static void memcg_create_cache_work_func(struct work_struct *w) +static void memcg_register_cache_func(struct work_struct *w) { - struct create_work *cw = container_of(w, struct create_work, work); + struct memcg_register_cache_work *cw = + container_of(w, struct memcg_register_cache_work, work); struct mem_cgroup *memcg = cw->memcg; struct kmem_cache *cachep = cw->cachep; - kmem_cache_create_memcg(memcg, cachep); + mutex_lock(&memcg_slab_mutex); + memcg_register_cache(memcg, cachep); + mutex_unlock(&memcg_slab_mutex); + css_put(&memcg->css); kfree(cw); } @@ -3412,12 +3159,12 @@ static void memcg_create_cache_work_func(struct work_struct *w) /* * Enqueue the creation of a per-memcg kmem_cache. */ -static void __memcg_create_cache_enqueue(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void __memcg_schedule_register_cache(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { - struct create_work *cw; + struct memcg_register_cache_work *cw; - cw = kmalloc(sizeof(struct create_work), GFP_NOWAIT); + cw = kmalloc(sizeof(*cw), GFP_NOWAIT); if (cw == NULL) { css_put(&memcg->css); return; @@ -3426,17 +3173,17 @@ static void __memcg_create_cache_enqueue(struct mem_cgroup *memcg, cw->memcg = memcg; cw->cachep = cachep; - INIT_WORK(&cw->work, memcg_create_cache_work_func); + INIT_WORK(&cw->work, memcg_register_cache_func); schedule_work(&cw->work); } -static void memcg_create_cache_enqueue(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void memcg_schedule_register_cache(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { /* * We need to stop accounting when we kmalloc, because if the * corresponding kmalloc cache is not yet created, the first allocation - * in __memcg_create_cache_enqueue will recurse. + * in __memcg_schedule_register_cache will recurse. * * However, it is better to enclose the whole function. Depending on * the debugging options enabled, INIT_WORK(), for instance, can @@ -3445,9 +3192,27 @@ static void memcg_create_cache_enqueue(struct mem_cgroup *memcg, * the safest choice is to do it like this, wrapping the whole function. */ memcg_stop_kmem_account(); - __memcg_create_cache_enqueue(memcg, cachep); + __memcg_schedule_register_cache(memcg, cachep); memcg_resume_kmem_account(); } + +int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order) +{ + int res; + + res = memcg_charge_kmem(cachep->memcg_params->memcg, gfp, + PAGE_SIZE << order); + if (!res) + atomic_add(1 << order, &cachep->memcg_params->nr_pages); + return res; +} + +void __memcg_uncharge_slab(struct kmem_cache *cachep, int order) +{ + memcg_uncharge_kmem(cachep->memcg_params->memcg, PAGE_SIZE << order); + atomic_sub(1 << order, &cachep->memcg_params->nr_pages); +} + /* * 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. @@ -3486,7 +3251,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, } /* The corresponding put will be done in the workqueue. */ - if (!css_tryget(&memcg->css)) + if (!css_tryget_online(&memcg->css)) goto out; rcu_read_unlock(); @@ -3498,22 +3263,16 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, * * However, there are some clashes that can arrive from locking. * For instance, because we acquire the slab_mutex while doing - * kmem_cache_dup, this means no further allocation could happen - * with the slab_mutex held. - * - * Also, because cache creation issue get_online_cpus(), this - * creates a lock chain: memcg_slab_mutex -> cpu_hotplug_mutex, - * that ends up reversed during cpu hotplug. (cpuset allocates - * a bunch of GFP_KERNEL memory during cpuup). Due to all that, - * better to defer everything. + * memcg_create_kmem_cache, this means no further allocation + * could happen with the slab_mutex held. So it's better to + * defer everything. */ - memcg_create_cache_enqueue(memcg, cachep); + memcg_schedule_register_cache(memcg, cachep); return cachep; out: rcu_read_unlock(); return cachep; } -EXPORT_SYMBOL(__memcg_kmem_get_cache); /* * We need to verify if the allocation against current->mm->owner's memcg is @@ -3540,11 +3299,12 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order) /* * Disabling accounting is only relevant for some specific memcg * internal allocations. Therefore we would initially not have such - * check here, since direct calls to the page allocator that are marked - * with GFP_KMEMCG only happen outside memcg core. We are mostly - * concerned with cache allocations, and by having this test at - * memcg_kmem_get_cache, we are already able to relay the allocation to - * the root cache and bypass the memcg cache altogether. + * check here, since direct calls to the page allocator that are + * accounted to kmemcg (alloc_kmem_pages and friends) only happen + * outside memcg core. We are mostly concerned with cache allocations, + * and by having this test at memcg_kmem_get_cache, we are already able + * to relay the allocation to the root cache and bypass the memcg cache + * altogether. * * There is one exception, though: the SLUB allocator does not create * large order caches, but rather service large kmallocs directly from @@ -3591,12 +3351,13 @@ void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, memcg_uncharge_kmem(memcg, PAGE_SIZE << order); return; } - + /* + * The page is freshly allocated and not visible to any + * outside callers yet. Set up pc non-atomically. + */ pc = lookup_page_cgroup(page); - lock_page_cgroup(pc); pc->mem_cgroup = memcg; - SetPageCgroupUsed(pc); - unlock_page_cgroup(pc); + pc->flags = PCG_USED; } void __memcg_kmem_uncharge_pages(struct page *page, int order) @@ -3606,19 +3367,11 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order) pc = lookup_page_cgroup(page); - /* - * Fast unlocked return. Theoretically might have changed, have to - * check again after locking. - */ if (!PageCgroupUsed(pc)) return; - lock_page_cgroup(pc); - if (PageCgroupUsed(pc)) { - memcg = pc->mem_cgroup; - ClearPageCgroupUsed(pc); - } - unlock_page_cgroup(pc); + memcg = pc->mem_cgroup; + pc->flags = 0; /* * We trust that only if there is a memcg associated with the page, it @@ -3631,14 +3384,13 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order) memcg_uncharge_kmem(memcg, PAGE_SIZE << order); } #else -static inline void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg) +static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg) { } #endif /* CONFIG_MEMCG_KMEM */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define PCGF_NOCOPY_AT_SPLIT (1 << PCG_LOCK | 1 << PCG_MIGRATION) /* * Because tail pages are not marked as "used", set it. We're under * zone->lru_lock, 'splitting on pmd' and compound_lock. @@ -3659,8 +3411,7 @@ void mem_cgroup_split_huge_fixup(struct page *head) for (i = 1; i < HPAGE_PMD_NR; i++) { pc = head_pc + i; pc->mem_cgroup = memcg; - smp_wmb();/* see __commit_charge() */ - pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT; + pc->flags = head_pc->flags; } __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], HPAGE_PMD_NR); @@ -3690,7 +3441,6 @@ static int mem_cgroup_move_account(struct page *page, { unsigned long flags; int ret; - bool anon = PageAnon(page); VM_BUG_ON(from == to); VM_BUG_ON_PAGE(PageLRU(page), page); @@ -3704,15 +3454,21 @@ static int mem_cgroup_move_account(struct page *page, if (nr_pages > 1 && !PageTransHuge(page)) goto out; - lock_page_cgroup(pc); + /* + * Prevent mem_cgroup_migrate() from looking at pc->mem_cgroup + * of its source page while we change it: page migration takes + * both pages off the LRU, but page cache replacement doesn't. + */ + if (!trylock_page(page)) + goto out; ret = -EINVAL; if (!PageCgroupUsed(pc) || pc->mem_cgroup != from) - goto unlock; + goto out_unlock; move_lock_mem_cgroup(from, &flags); - if (!anon && page_mapped(page)) { + if (!PageAnon(page) && page_mapped(page)) { __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], nr_pages); __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], @@ -3726,20 +3482,25 @@ static int mem_cgroup_move_account(struct page *page, nr_pages); } - mem_cgroup_charge_statistics(from, page, anon, -nr_pages); + /* + * It is safe to change pc->mem_cgroup here because the page + * is referenced, charged, and isolated - we can't race with + * uncharging, charging, migration, or LRU putback. + */ /* caller should have done css_get */ pc->mem_cgroup = to; - mem_cgroup_charge_statistics(to, page, anon, nr_pages); move_unlock_mem_cgroup(from, &flags); ret = 0; -unlock: - unlock_page_cgroup(pc); - /* - * check events - */ + + local_irq_disable(); + mem_cgroup_charge_statistics(to, page, nr_pages); memcg_check_events(to, page); + mem_cgroup_charge_statistics(from, page, -nr_pages); memcg_check_events(from, page); + local_irq_enable(); +out_unlock: + unlock_page(page); out: return ret; } @@ -3810,456 +3571,12 @@ out: return ret; } -int mem_cgroup_charge_anon(struct page *page, - struct mm_struct *mm, gfp_t gfp_mask) -{ - unsigned int nr_pages = 1; - struct mem_cgroup *memcg; - bool oom = true; - - if (mem_cgroup_disabled()) - return 0; - - VM_BUG_ON_PAGE(page_mapped(page), page); - VM_BUG_ON_PAGE(page->mapping && !PageAnon(page), page); - VM_BUG_ON(!mm); - - if (PageTransHuge(page)) { - nr_pages <<= compound_order(page); - VM_BUG_ON_PAGE(!PageTransHuge(page), page); - /* - * Never OOM-kill a process for a huge page. The - * fault handler will fall back to regular pages. - */ - oom = false; - } - - memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, nr_pages, oom); - if (!memcg) - return -ENOMEM; - __mem_cgroup_commit_charge(memcg, page, nr_pages, - MEM_CGROUP_CHARGE_TYPE_ANON, false); - return 0; -} - -/* - * While swap-in, try_charge -> commit or cancel, the page is locked. - * And when try_charge() successfully returns, one refcnt to memcg without - * struct page_cgroup is acquired. This refcnt will be consumed by - * "commit()" or removed by "cancel()" - */ -static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm, - struct page *page, - gfp_t mask, - struct mem_cgroup **memcgp) -{ - struct mem_cgroup *memcg = NULL; - struct page_cgroup *pc; - int ret; - - pc = lookup_page_cgroup(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. - */ - if (PageCgroupUsed(pc)) - goto out; - if (do_swap_account) - memcg = try_get_mem_cgroup_from_page(page); - if (!memcg) - memcg = get_mem_cgroup_from_mm(mm); - ret = mem_cgroup_try_charge(memcg, mask, 1, true); - css_put(&memcg->css); - if (ret == -EINTR) - memcg = root_mem_cgroup; - else if (ret) - return ret; -out: - *memcgp = memcg; - return 0; -} - -int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page, - gfp_t gfp_mask, struct mem_cgroup **memcgp) -{ - if (mem_cgroup_disabled()) { - *memcgp = NULL; - return 0; - } - /* - * A racing thread's fault, or swapoff, may have already - * updated the pte, and even removed page from swap cache: in - * those cases unuse_pte()'s pte_same() test will fail; but - * there's also a KSM case which does need to charge the page. - */ - if (!PageSwapCache(page)) { - struct mem_cgroup *memcg; - - memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true); - if (!memcg) - return -ENOMEM; - *memcgp = memcg; - return 0; - } - return __mem_cgroup_try_charge_swapin(mm, page, gfp_mask, memcgp); -} - -void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg) -{ - if (mem_cgroup_disabled()) - return; - if (!memcg) - return; - __mem_cgroup_cancel_charge(memcg, 1); -} - -static void -__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg, - enum charge_type ctype) -{ - if (mem_cgroup_disabled()) - return; - if (!memcg) - return; - - __mem_cgroup_commit_charge(memcg, page, 1, ctype, true); - /* - * Now swap is on-memory. This means this page may be - * counted both as mem and swap....double count. - * Fix it by uncharging from memsw. Basically, this SwapCache is stable - * under lock_page(). But in do_swap_page()::memory.c, reuse_swap_page() - * may call delete_from_swap_cache() before reach here. - */ - if (do_swap_account && PageSwapCache(page)) { - swp_entry_t ent = {.val = page_private(page)}; - mem_cgroup_uncharge_swap(ent); - } -} - -void mem_cgroup_commit_charge_swapin(struct page *page, - struct mem_cgroup *memcg) -{ - __mem_cgroup_commit_charge_swapin(page, memcg, - MEM_CGROUP_CHARGE_TYPE_ANON); -} - -int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask) -{ - enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE; - struct mem_cgroup *memcg; - int ret; - - if (mem_cgroup_disabled()) - return 0; - if (PageCompound(page)) - return 0; - - if (PageSwapCache(page)) { /* shmem */ - ret = __mem_cgroup_try_charge_swapin(mm, page, - gfp_mask, &memcg); - if (ret) - return ret; - __mem_cgroup_commit_charge_swapin(page, memcg, type); - return 0; - } - - memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true); - if (!memcg) - return -ENOMEM; - __mem_cgroup_commit_charge(memcg, page, 1, type, false); - return 0; -} - -static void mem_cgroup_do_uncharge(struct mem_cgroup *memcg, - unsigned int nr_pages, - const enum charge_type ctype) -{ - struct memcg_batch_info *batch = NULL; - bool uncharge_memsw = true; - - /* If swapout, usage of swap doesn't decrease */ - if (!do_swap_account || ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) - uncharge_memsw = false; - - batch = ¤t->memcg_batch; - /* - * In usual, we do css_get() when we remember memcg pointer. - * But in this case, we keep res->usage until end of a series of - * uncharges. Then, it's ok to ignore memcg's refcnt. - */ - if (!batch->memcg) - batch->memcg = memcg; - /* - * do_batch > 0 when unmapping pages or inode invalidate/truncate. - * In those cases, all pages freed continuously can be expected to be in - * the same cgroup and we have chance to coalesce uncharges. - * But we do uncharge one by one if this is killed by OOM(TIF_MEMDIE) - * because we want to do uncharge as soon as possible. - */ - - if (!batch->do_batch || test_thread_flag(TIF_MEMDIE)) - goto direct_uncharge; - - if (nr_pages > 1) - goto direct_uncharge; - - /* - * In typical case, batch->memcg == mem. This means we can - * merge a series of uncharges to an uncharge of res_counter. - * If not, we uncharge res_counter ony by one. - */ - if (batch->memcg != memcg) - goto direct_uncharge; - /* remember freed charge and uncharge it later */ - batch->nr_pages++; - if (uncharge_memsw) - batch->memsw_nr_pages++; - return; -direct_uncharge: - res_counter_uncharge(&memcg->res, nr_pages * PAGE_SIZE); - if (uncharge_memsw) - res_counter_uncharge(&memcg->memsw, nr_pages * PAGE_SIZE); - if (unlikely(batch->memcg != memcg)) - memcg_oom_recover(memcg); -} - -/* - * uncharge if !page_mapped(page) - */ -static struct mem_cgroup * -__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype, - bool end_migration) -{ - struct mem_cgroup *memcg = NULL; - unsigned int nr_pages = 1; - struct page_cgroup *pc; - bool anon; - - if (mem_cgroup_disabled()) - return NULL; - - if (PageTransHuge(page)) { - nr_pages <<= compound_order(page); - VM_BUG_ON_PAGE(!PageTransHuge(page), page); - } - /* - * Check if our page_cgroup is valid - */ - pc = lookup_page_cgroup(page); - if (unlikely(!PageCgroupUsed(pc))) - return NULL; - - lock_page_cgroup(pc); - - memcg = pc->mem_cgroup; - - if (!PageCgroupUsed(pc)) - goto unlock_out; - - anon = PageAnon(page); - - switch (ctype) { - case MEM_CGROUP_CHARGE_TYPE_ANON: - /* - * Generally PageAnon tells if it's the anon statistics to be - * updated; but sometimes e.g. mem_cgroup_uncharge_page() is - * used before page reached the stage of being marked PageAnon. - */ - anon = true; - /* fallthrough */ - case MEM_CGROUP_CHARGE_TYPE_DROP: - /* See mem_cgroup_prepare_migration() */ - if (page_mapped(page)) - goto unlock_out; - /* - * Pages under migration may not be uncharged. But - * end_migration() /must/ be the one uncharging the - * unused post-migration page and so it has to call - * here with the migration bit still set. See the - * res_counter handling below. - */ - if (!end_migration && PageCgroupMigration(pc)) - goto unlock_out; - break; - case MEM_CGROUP_CHARGE_TYPE_SWAPOUT: - if (!PageAnon(page)) { /* Shared memory */ - if (page->mapping && !page_is_file_cache(page)) - goto unlock_out; - } else if (page_mapped(page)) /* Anon */ - goto unlock_out; - break; - default: - break; - } - - mem_cgroup_charge_statistics(memcg, page, anon, -nr_pages); - - ClearPageCgroupUsed(pc); - /* - * pc->mem_cgroup is not cleared here. It will be accessed when it's - * freed from LRU. This is safe because uncharged page is expected not - * to be reused (freed soon). Exception is SwapCache, it's handled by - * special functions. - */ - - unlock_page_cgroup(pc); - /* - * even after unlock, we have memcg->res.usage here and this memcg - * will never be freed, so it's safe to call css_get(). - */ - memcg_check_events(memcg, page); - if (do_swap_account && ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) { - mem_cgroup_swap_statistics(memcg, true); - css_get(&memcg->css); - } - /* - * Migration does not charge the res_counter for the - * replacement page, so leave it alone when phasing out the - * page that is unused after the migration. - */ - if (!end_migration && !mem_cgroup_is_root(memcg)) - mem_cgroup_do_uncharge(memcg, nr_pages, ctype); - - return memcg; - -unlock_out: - unlock_page_cgroup(pc); - return NULL; -} - -void mem_cgroup_uncharge_page(struct page *page) -{ - /* early check. */ - if (page_mapped(page)) - return; - VM_BUG_ON_PAGE(page->mapping && !PageAnon(page), page); - /* - * If the page is in swap cache, uncharge should be deferred - * to the swap path, which also properly accounts swap usage - * and handles memcg lifetime. - * - * Note that this check is not stable and reclaim may add the - * page to swap cache at any time after this. However, if the - * page is not in swap cache by the time page->mapcount hits - * 0, there won't be any page table references to the swap - * slot, and reclaim will free it and not actually write the - * page to disk. - */ - if (PageSwapCache(page)) - return; - __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_ANON, false); -} - -void mem_cgroup_uncharge_cache_page(struct page *page) -{ - VM_BUG_ON_PAGE(page_mapped(page), page); - VM_BUG_ON_PAGE(page->mapping, page); - __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE, false); -} - -/* - * Batch_start/batch_end is called in unmap_page_range/invlidate/trucate. - * In that cases, pages are freed continuously and we can expect pages - * are in the same memcg. All these calls itself limits the number of - * pages freed at once, then uncharge_start/end() is called properly. - * This may be called prural(2) times in a context, - */ - -void mem_cgroup_uncharge_start(void) -{ - current->memcg_batch.do_batch++; - /* We can do nest. */ - if (current->memcg_batch.do_batch == 1) { - current->memcg_batch.memcg = NULL; - current->memcg_batch.nr_pages = 0; - current->memcg_batch.memsw_nr_pages = 0; - } -} - -void mem_cgroup_uncharge_end(void) -{ - struct memcg_batch_info *batch = ¤t->memcg_batch; - - if (!batch->do_batch) - return; - - batch->do_batch--; - if (batch->do_batch) /* If stacked, do nothing. */ - return; - - if (!batch->memcg) - return; - /* - * This "batch->memcg" is valid without any css_get/put etc... - * bacause we hide charges behind us. - */ - if (batch->nr_pages) - res_counter_uncharge(&batch->memcg->res, - batch->nr_pages * PAGE_SIZE); - if (batch->memsw_nr_pages) - res_counter_uncharge(&batch->memcg->memsw, - batch->memsw_nr_pages * PAGE_SIZE); - memcg_oom_recover(batch->memcg); - /* forget this pointer (for sanity check) */ - batch->memcg = NULL; -} - -#ifdef CONFIG_SWAP -/* - * called after __delete_from_swap_cache() and drop "page" account. - * memcg information is recorded to swap_cgroup of "ent" - */ -void -mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) -{ - struct mem_cgroup *memcg; - int ctype = MEM_CGROUP_CHARGE_TYPE_SWAPOUT; - - if (!swapout) /* this was a swap cache but the swap is unused ! */ - ctype = MEM_CGROUP_CHARGE_TYPE_DROP; - - memcg = __mem_cgroup_uncharge_common(page, ctype, false); - - /* - * record memcg information, if swapout && memcg != NULL, - * css_get() was called in uncharge(). - */ - if (do_swap_account && swapout && memcg) - swap_cgroup_record(ent, mem_cgroup_id(memcg)); -} -#endif - #ifdef CONFIG_MEMCG_SWAP -/* - * called from swap_entry_free(). remove record in swap_cgroup and - * uncharge "memsw" account. - */ -void mem_cgroup_uncharge_swap(swp_entry_t ent) +static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg, + bool charge) { - struct mem_cgroup *memcg; - unsigned short id; - - if (!do_swap_account) - return; - - id = swap_cgroup_record(ent, 0); - rcu_read_lock(); - memcg = mem_cgroup_lookup(id); - if (memcg) { - /* - * We uncharge this because swap is freed. - * This memcg can be obsolete one. We avoid calling css_tryget - */ - if (!mem_cgroup_is_root(memcg)) - res_counter_uncharge(&memcg->memsw, PAGE_SIZE); - mem_cgroup_swap_statistics(memcg, false); - css_put(&memcg->css); - } - rcu_read_unlock(); + int val = (charge) ? 1 : -1; + this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAP], val); } /** @@ -4311,175 +3628,6 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry, } #endif -/* - * Before starting migration, account PAGE_SIZE to mem_cgroup that the old - * page belongs to. - */ -void mem_cgroup_prepare_migration(struct page *page, struct page *newpage, - struct mem_cgroup **memcgp) -{ - struct mem_cgroup *memcg = NULL; - unsigned int nr_pages = 1; - struct page_cgroup *pc; - enum charge_type ctype; - - *memcgp = NULL; - - if (mem_cgroup_disabled()) - return; - - if (PageTransHuge(page)) - nr_pages <<= compound_order(page); - - pc = lookup_page_cgroup(page); - lock_page_cgroup(pc); - if (PageCgroupUsed(pc)) { - memcg = pc->mem_cgroup; - css_get(&memcg->css); - /* - * At migrating an anonymous page, its mapcount goes down - * to 0 and uncharge() will be called. But, even if it's fully - * unmapped, migration may fail and this page has to be - * charged again. We set MIGRATION flag here and delay uncharge - * until end_migration() is called - * - * Corner Case Thinking - * A) - * When the old page was mapped as Anon and it's unmap-and-freed - * while migration was ongoing. - * If unmap finds the old page, uncharge() of it will be delayed - * until end_migration(). If unmap finds a new page, it's - * uncharged when it make mapcount to be 1->0. If unmap code - * finds swap_migration_entry, the new page will not be mapped - * and end_migration() will find it(mapcount==0). - * - * B) - * When the old page was mapped but migraion fails, the kernel - * remaps it. A charge for it is kept by MIGRATION flag even - * if mapcount goes down to 0. We can do remap successfully - * without charging it again. - * - * C) - * The "old" page is under lock_page() until the end of - * migration, so, the old page itself will not be swapped-out. - * If the new page is swapped out before end_migraton, our - * hook to usual swap-out path will catch the event. - */ - if (PageAnon(page)) - SetPageCgroupMigration(pc); - } - unlock_page_cgroup(pc); - /* - * If the page is not charged at this point, - * we return here. - */ - if (!memcg) - return; - - *memcgp = memcg; - /* - * We charge new page before it's used/mapped. So, even if unlock_page() - * is called before end_migration, we can catch all events on this new - * page. In the case new page is migrated but not remapped, new page's - * mapcount will be finally 0 and we call uncharge in end_migration(). - */ - if (PageAnon(page)) - ctype = MEM_CGROUP_CHARGE_TYPE_ANON; - else - ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; - /* - * The page is committed to the memcg, but it's not actually - * charged to the res_counter since we plan on replacing the - * old one and only one page is going to be left afterwards. - */ - __mem_cgroup_commit_charge(memcg, newpage, nr_pages, ctype, false); -} - -/* remove redundant charge if migration failed*/ -void mem_cgroup_end_migration(struct mem_cgroup *memcg, - struct page *oldpage, struct page *newpage, bool migration_ok) -{ - struct page *used, *unused; - struct page_cgroup *pc; - bool anon; - - if (!memcg) - return; - - if (!migration_ok) { - used = oldpage; - unused = newpage; - } else { - used = newpage; - unused = oldpage; - } - anon = PageAnon(used); - __mem_cgroup_uncharge_common(unused, - anon ? MEM_CGROUP_CHARGE_TYPE_ANON - : MEM_CGROUP_CHARGE_TYPE_CACHE, - true); - css_put(&memcg->css); - /* - * We disallowed uncharge of pages under migration because mapcount - * of the page goes down to zero, temporarly. - * Clear the flag and check the page should be charged. - */ - pc = lookup_page_cgroup(oldpage); - lock_page_cgroup(pc); - ClearPageCgroupMigration(pc); - unlock_page_cgroup(pc); - - /* - * If a page is a file cache, radix-tree replacement is very atomic - * and we can skip this check. When it was an Anon page, its mapcount - * goes down to 0. But because we added MIGRATION flage, it's not - * uncharged yet. There are several case but page->mapcount check - * and USED bit check in mem_cgroup_uncharge_page() will do enough - * check. (see prepare_charge() also) - */ - if (anon) - mem_cgroup_uncharge_page(used); -} - -/* - * At replace page cache, newpage is not under any memcg but it's on - * LRU. So, this function doesn't touch res_counter but handles LRU - * in correct way. Both pages are locked so we cannot race with uncharge. - */ -void mem_cgroup_replace_page_cache(struct page *oldpage, - struct page *newpage) -{ - struct mem_cgroup *memcg = NULL; - struct page_cgroup *pc; - enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE; - - if (mem_cgroup_disabled()) - return; - - pc = lookup_page_cgroup(oldpage); - /* fix accounting on old pages */ - lock_page_cgroup(pc); - if (PageCgroupUsed(pc)) { - memcg = pc->mem_cgroup; - mem_cgroup_charge_statistics(memcg, oldpage, false, -1); - ClearPageCgroupUsed(pc); - } - unlock_page_cgroup(pc); - - /* - * When called from shmem_replace_page(), in some cases the - * oldpage has already been charged, and in some cases not. - */ - if (!memcg) - return; - /* - * Even if newpage->mapping was NULL before starting replacement, - * the newpage may be on LRU(or pagevec for LRU) already. We lock - * LRU while we overwrite pc->mem_cgroup. - */ - __mem_cgroup_commit_charge(memcg, newpage, 1, type, true); -} - #ifdef CONFIG_DEBUG_VM static struct page_cgroup *lookup_page_cgroup_used(struct page *page) { @@ -4678,7 +3826,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, gfp_mask, &nr_scanned); nr_reclaimed += reclaimed; *total_scanned += nr_scanned; - spin_lock(&mctz->lock); + spin_lock_irq(&mctz->lock); /* * If we failed to reclaim anything from this memory cgroup @@ -4706,7 +3854,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, break; } while (1); } - __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz); + __mem_cgroup_remove_exceeded(mz, mctz); excess = res_counter_soft_limit_excess(&mz->memcg->res); /* * One school of thought says that we should not add @@ -4717,8 +3865,8 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, * term TODO. */ /* If excess == 0, no tree ops */ - __mem_cgroup_insert_exceeded(mz->memcg, mz, mctz, excess); - spin_unlock(&mctz->lock); + __mem_cgroup_insert_exceeded(mz, mctz, excess); + spin_unlock_irq(&mctz->lock); css_put(&mz->memcg->css); loop++; /* @@ -4784,9 +3932,9 @@ static void mem_cgroup_force_empty_list(struct mem_cgroup *memcg, if (mem_cgroup_move_parent(page, pc, memcg)) { /* found lock contention or "pc" is obsolete. */ busy = page; - cond_resched(); } else busy = NULL; + cond_resched(); } while (!list_empty(list)); } @@ -4837,18 +3985,28 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg) } while (usage > 0); } +/* + * 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) { - lockdep_assert_held(&memcg_create_mutex); + bool ret; + /* - * The lock does not prevent addition or deletion to the list - * of children, but it prevents a new child from being - * initialized based on this parent in css_online(), so it's - * enough to decide whether hierarchically inherited - * attributes can still be changed or not. + * The lock does not prevent addition or deletion of children, but + * it prevents a new child from being initialized based on this + * parent in css_online(), so it's enough to decide whether + * hierarchically inherited attributes can still be changed or not. */ - return memcg->use_hierarchy && - !list_empty(&memcg->css.cgroup->children); + lockdep_assert_held(&memcg_create_mutex); + + rcu_read_lock(); + ret = css_next_child(NULL, &memcg->css); + rcu_read_unlock(); + return ret; } /* @@ -4860,11 +4018,6 @@ static inline bool memcg_has_children(struct mem_cgroup *memcg) static int mem_cgroup_force_empty(struct mem_cgroup *memcg) { int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; - struct cgroup *cgrp = memcg->css.cgroup; - - /* returns EBUSY if there is a task or if we come here twice. */ - if (cgroup_has_tasks(cgrp) || !list_empty(&cgrp->children)) - return -EBUSY; /* we call try-to-free pages for make this cgroup empty */ lru_add_drain_all(); @@ -4884,20 +4037,19 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) } } - lru_add_drain(); - mem_cgroup_reparent_charges(memcg); return 0; } -static int mem_cgroup_force_empty_write(struct cgroup_subsys_state *css, - unsigned int event) +static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + 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); + return mem_cgroup_force_empty(memcg) ?: nbytes; } static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css, @@ -4911,7 +4063,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, { int retval = 0; struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct mem_cgroup *parent_memcg = mem_cgroup_from_css(css_parent(&memcg->css)); + struct mem_cgroup *parent_memcg = mem_cgroup_from_css(memcg->css.parent); mutex_lock(&memcg_create_mutex); @@ -4928,7 +4080,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, */ if ((!parent_memcg || !parent_memcg->use_hierarchy) && (val == 1 || val == 0)) { - if (list_empty(&memcg->css.cgroup->children)) + if (!memcg_has_children(memcg)) memcg->use_hierarchy = val; else retval = -EBUSY; @@ -4941,78 +4093,24 @@ out: return retval; } - -static unsigned long mem_cgroup_recursive_stat(struct mem_cgroup *memcg, - enum mem_cgroup_stat_index idx) -{ - struct mem_cgroup *iter; - long val = 0; - - /* Per-cpu values can be negative, use a signed accumulator */ - for_each_mem_cgroup_tree(iter, memcg) - val += mem_cgroup_read_stat(iter, idx); - - if (val < 0) /* race ? */ - val = 0; - return val; -} - -static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) -{ - u64 val; - - if (!mem_cgroup_is_root(memcg)) { - if (!swap) - return res_counter_read_u64(&memcg->res, RES_USAGE); - else - return res_counter_read_u64(&memcg->memsw, RES_USAGE); - } - - /* - * Transparent hugepages are still accounted for in MEM_CGROUP_STAT_RSS - * as well as in MEM_CGROUP_STAT_RSS_HUGE. - */ - val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE); - val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS); - - if (swap) - val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAP); - - return val << PAGE_SHIFT; -} - static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, - struct cftype *cft) + struct cftype *cft) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - u64 val; - int name; - enum res_type type; - - type = MEMFILE_TYPE(cft->private); - name = MEMFILE_ATTR(cft->private); + enum res_type type = MEMFILE_TYPE(cft->private); + int name = MEMFILE_ATTR(cft->private); switch (type) { case _MEM: - if (name == RES_USAGE) - val = mem_cgroup_usage(memcg, false); - else - val = res_counter_read_u64(&memcg->res, name); - break; + return res_counter_read_u64(&memcg->res, name); case _MEMSWAP: - if (name == RES_USAGE) - val = mem_cgroup_usage(memcg, true); - else - val = res_counter_read_u64(&memcg->memsw, name); - break; + return res_counter_read_u64(&memcg->memsw, name); case _KMEM: - val = res_counter_read_u64(&memcg->kmem, name); + return res_counter_read_u64(&memcg->kmem, name); break; default: BUG(); } - - return val; } #ifdef CONFIG_MEMCG_KMEM @@ -5045,7 +4143,8 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg, * of course permitted. */ mutex_lock(&memcg_create_mutex); - if (cgroup_has_tasks(memcg->css.cgroup) || memcg_has_children(memcg)) + if (cgroup_has_tasks(memcg->css.cgroup) || + (memcg->use_hierarchy && memcg_has_children(memcg))) err = -EBUSY; mutex_unlock(&memcg_create_mutex); if (err) @@ -5062,13 +4161,14 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg, * Make sure we have enough space for this cgroup in each root cache's * memcg_params. */ + mutex_lock(&memcg_slab_mutex); err = memcg_update_all_caches(memcg_id + 1); + mutex_unlock(&memcg_slab_mutex); if (err) goto out_rmid; memcg->kmemcg_id = memcg_id; INIT_LIST_HEAD(&memcg->memcg_slab_caches); - mutex_init(&memcg->slab_caches_mutex); /* * We couldn't have accounted to this cgroup, because it hasn't got the @@ -5146,17 +4246,18 @@ static int memcg_update_kmem_limit(struct mem_cgroup *memcg, * The user of this function is... * RES_LIMIT. */ -static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, - char *buffer) +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(css); + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); enum res_type type; int name; unsigned long long val; int ret; - type = MEMFILE_TYPE(cft->private); - name = MEMFILE_ATTR(cft->private); + buf = strstrip(buf); + type = MEMFILE_TYPE(of_cft(of)->private); + name = MEMFILE_ATTR(of_cft(of)->private); switch (name) { case RES_LIMIT: @@ -5165,7 +4266,7 @@ static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, break; } /* This function does all necessary parse...reuse it */ - ret = res_counter_memparse_write_strategy(buffer, &val); + ret = res_counter_memparse_write_strategy(buf, &val); if (ret) break; if (type == _MEM) @@ -5178,7 +4279,7 @@ static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, return -EINVAL; break; case RES_SOFT_LIMIT: - ret = res_counter_memparse_write_strategy(buffer, &val); + ret = res_counter_memparse_write_strategy(buf, &val); if (ret) break; /* @@ -5195,7 +4296,7 @@ static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, ret = -EINVAL; /* should be BUG() ? */ break; } - return ret; + return ret ?: nbytes; } static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg, @@ -5208,8 +4309,8 @@ static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg, if (!memcg->use_hierarchy) goto out; - while (css_parent(&memcg->css)) { - memcg = mem_cgroup_from_css(css_parent(&memcg->css)); + while (memcg->css.parent) { + memcg = mem_cgroup_from_css(memcg->css.parent); if (!memcg->use_hierarchy) break; tmp = res_counter_read_u64(&memcg->res, RES_LIMIT); @@ -5222,14 +4323,15 @@ out: *memsw_limit = min_memsw_limit; } -static int mem_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event) +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(css); + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); int name; enum res_type type; - type = MEMFILE_TYPE(event); - name = MEMFILE_ATTR(event); + type = MEMFILE_TYPE(of_cft(of)->private); + name = MEMFILE_ATTR(of_cft(of)->private); switch (name) { case RES_MAX_USAGE: @@ -5254,7 +4356,7 @@ static int mem_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event) break; } - return 0; + return nbytes; } static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css, @@ -5413,7 +4515,7 @@ static int memcg_stat_show(struct seq_file *m, void *v) for_each_online_node(nid) for (zid = 0; zid < MAX_NR_ZONES; zid++) { - mz = mem_cgroup_zoneinfo(memcg, nid, zid); + mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; rstat = &mz->lruvec.reclaim_stat; recent_rotated[0] += rstat->recent_rotated[0]; @@ -5443,22 +4545,14 @@ 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); - struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css)); - if (val > 100 || !parent) + if (val > 100) return -EINVAL; - mutex_lock(&memcg_create_mutex); - - /* If under hierarchy, only empty-root can set this value */ - if ((parent->use_hierarchy) || memcg_has_children(memcg)) { - mutex_unlock(&memcg_create_mutex); - return -EINVAL; - } - - memcg->swappiness = val; - - mutex_unlock(&memcg_create_mutex); + if (css->parent) + memcg->swappiness = val; + else + vm_swappiness = val; return 0; } @@ -5478,7 +4572,10 @@ static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap) if (!t) goto unlock; - usage = mem_cgroup_usage(memcg, swap); + if (!swap) + usage = res_counter_read_u64(&memcg->res, RES_USAGE); + else + usage = res_counter_read_u64(&memcg->memsw, RES_USAGE); /* * current_threshold points to threshold just below or equal to usage. @@ -5543,8 +4640,12 @@ static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg) { 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; } @@ -5570,15 +4671,15 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg, mutex_lock(&memcg->thresholds_lock); - if (type == _MEM) + if (type == _MEM) { thresholds = &memcg->thresholds; - else if (type == _MEMSWAP) + usage = res_counter_read_u64(&memcg->res, RES_USAGE); + } else if (type == _MEMSWAP) { thresholds = &memcg->memsw_thresholds; - else + usage = res_counter_read_u64(&memcg->memsw, RES_USAGE); + } else BUG(); - usage = mem_cgroup_usage(memcg, type == _MEMSWAP); - /* Check if a threshold crossed before adding a new one */ if (thresholds->primary) __mem_cgroup_threshold(memcg, type == _MEMSWAP); @@ -5658,18 +4759,19 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, int i, j, size; mutex_lock(&memcg->thresholds_lock); - if (type == _MEM) + + if (type == _MEM) { thresholds = &memcg->thresholds; - else if (type == _MEMSWAP) + usage = res_counter_read_u64(&memcg->res, RES_USAGE); + } else if (type == _MEMSWAP) { thresholds = &memcg->memsw_thresholds; - else + usage = res_counter_read_u64(&memcg->memsw, RES_USAGE); + } else BUG(); if (!thresholds->primary) goto unlock; - usage = mem_cgroup_usage(memcg, type == _MEMSWAP); - /* Check if a threshold crossed before removing */ __mem_cgroup_threshold(memcg, type == _MEMSWAP); @@ -5790,22 +4892,15 @@ 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); - struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css)); /* cannot set to root cgroup and only 0 and 1 are allowed */ - if (!parent || !((val == 0) || (val == 1))) + if (!css->parent || !((val == 0) || (val == 1))) return -EINVAL; - mutex_lock(&memcg_create_mutex); - /* oom-kill-disable is a flag for subhierarchy. */ - if ((parent->use_hierarchy) || memcg_has_children(memcg)) { - mutex_unlock(&memcg_create_mutex); - return -EINVAL; - } memcg->oom_kill_disable = val; if (!val) memcg_oom_recover(memcg); - mutex_unlock(&memcg_create_mutex); + return 0; } @@ -5845,10 +4940,10 @@ static void kmem_cgroup_css_offline(struct mem_cgroup *memcg) * which is then paired with css_put during uncharge resp. here. * * Although this might sound strange as this path is called from - * css_offline() when the referencemight have dropped down to 0 - * and shouldn't be incremented anymore (css_tryget would fail) - * we do not have other options because of the kmem allocations - * lifetime. + * css_offline() when the referencemight have dropped down to 0 and + * shouldn't be incremented anymore (css_tryget_online() would + * fail) we do not have other options because of the kmem + * allocations lifetime. */ css_get(&memcg->css); @@ -5967,9 +5062,10 @@ static void memcg_event_ptable_queue_proc(struct file *file, * Input must be in format '<event_fd> <control_fd> <args>'. * Interpretation of args is defined by control file implementation. */ -static int memcg_write_event_control(struct cgroup_subsys_state *css, - struct cftype *cft, char *buffer) +static ssize_t memcg_write_event_control(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { + 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; @@ -5980,15 +5076,17 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css, char *endp; int ret; - efd = simple_strtoul(buffer, &endp, 10); + buf = strstrip(buf); + + efd = simple_strtoul(buf, &endp, 10); if (*endp != ' ') return -EINVAL; - buffer = endp + 1; + buf = endp + 1; - cfd = simple_strtoul(buffer, &endp, 10); + cfd = simple_strtoul(buf, &endp, 10); if ((*endp != ' ') && (*endp != '\0')) return -EINVAL; - buffer = endp + 1; + buf = endp + 1; event = kzalloc(sizeof(*event), GFP_KERNEL); if (!event) @@ -6056,8 +5154,8 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css, * automatically removed on cgroup destruction but the removal is * asynchronous, so take an extra ref on @css. */ - cfile_css = css_tryget_from_dir(cfile.file->f_dentry->d_parent, - &memory_cgrp_subsys); + cfile_css = css_tryget_online_from_dir(cfile.file->f_dentry->d_parent, + &memory_cgrp_subsys); ret = -EINVAL; if (IS_ERR(cfile_css)) goto out_put_cfile; @@ -6066,7 +5164,7 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css, goto out_put_cfile; } - ret = event->register_event(memcg, event->eventfd, buffer); + ret = event->register_event(memcg, event->eventfd, buf); if (ret) goto out_put_css; @@ -6079,7 +5177,7 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css, fdput(cfile); fdput(efile); - return 0; + return nbytes; out_put_css: css_put(css); @@ -6104,25 +5202,25 @@ static struct cftype mem_cgroup_files[] = { { .name = "max_usage_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, { .name = "limit_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_LIMIT), - .write_string = mem_cgroup_write, + .write = mem_cgroup_write, .read_u64 = mem_cgroup_read_u64, }, { .name = "soft_limit_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT), - .write_string = mem_cgroup_write, + .write = mem_cgroup_write, .read_u64 = mem_cgroup_read_u64, }, { .name = "failcnt", .private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, { @@ -6131,17 +5229,16 @@ static struct cftype mem_cgroup_files[] = { }, { .name = "force_empty", - .trigger = mem_cgroup_force_empty_write, + .write = mem_cgroup_force_empty_write, }, { .name = "use_hierarchy", - .flags = CFTYPE_INSANE, .write_u64 = mem_cgroup_hierarchy_write, .read_u64 = mem_cgroup_hierarchy_read, }, { .name = "cgroup.event_control", /* XXX: for compat */ - .write_string = memcg_write_event_control, + .write = memcg_write_event_control, .flags = CFTYPE_NO_PREFIX, .mode = S_IWUGO, }, @@ -6174,7 +5271,7 @@ static struct cftype mem_cgroup_files[] = { { .name = "kmem.limit_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT), - .write_string = mem_cgroup_write, + .write = mem_cgroup_write, .read_u64 = mem_cgroup_read_u64, }, { @@ -6185,13 +5282,13 @@ static struct cftype mem_cgroup_files[] = { { .name = "kmem.failcnt", .private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, { .name = "kmem.max_usage_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, #ifdef CONFIG_SLABINFO @@ -6214,19 +5311,19 @@ static struct cftype memsw_cgroup_files[] = { { .name = "memsw.max_usage_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, { .name = "memsw.limit_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), - .write_string = mem_cgroup_write, + .write = mem_cgroup_write, .read_u64 = mem_cgroup_read_u64, }, { .name = "memsw.failcnt", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), - .trigger = mem_cgroup_reset, + .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, { }, /* terminate */ @@ -6404,9 +5501,9 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css)); + struct mem_cgroup *parent = mem_cgroup_from_css(css->parent); - if (css->cgroup->id > MEM_CGROUP_ID_MAX) + if (css->id > MEM_CGROUP_ID_MAX) return -ENOSPC; if (!parent) @@ -6428,9 +5525,9 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) * core guarantees its existence. */ } else { - res_counter_init(&memcg->res, NULL); - res_counter_init(&memcg->memsw, NULL); - res_counter_init(&memcg->kmem, NULL); + res_counter_init(&memcg->res, &root_mem_cgroup->res); + res_counter_init(&memcg->memsw, &root_mem_cgroup->memsw); + res_counter_init(&memcg->kmem, &root_mem_cgroup->kmem); /* * Deeper hierachy with use_hierarchy == false doesn't make * much sense so let cgroup subsystem know about this @@ -6491,7 +5588,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) css_for_each_descendant_post(iter, css) mem_cgroup_reparent_charges(mem_cgroup_from_css(iter)); - mem_cgroup_destroy_all_caches(memcg); + memcg_unregister_all_caches(memcg); vmpressure_cleanup(&memcg->vmpressure); } @@ -6501,7 +5598,7 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) /* * XXX: css_offline() would be where we should reparent all * memory to prepare the cgroup for destruction. However, - * memcg does not do css_tryget() and res_counter charging + * memcg does not do css_tryget_online() and res_counter charging * under the same RCU lock region, which means that charging * could race with offlining. Offlining only happens to * cgroups with no tasks in them but charges can show up @@ -6515,9 +5612,9 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) * lookup_swap_cgroup_id() * rcu_read_lock() * mem_cgroup_lookup() - * css_tryget() + * css_tryget_online() * rcu_read_unlock() - * disable css_tryget() + * disable css_tryget_online() * call_rcu() * offline_css() * reparent_charges() @@ -6539,57 +5636,63 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) __mem_cgroup_free(memcg); } +/** + * mem_cgroup_css_reset - reset the states of a mem_cgroup + * @css: the target css + * + * Reset the states of the mem_cgroup associated with @css. This is + * invoked when the userland requests disabling on the default hierarchy + * but the memcg is pinned through dependency. The memcg should stop + * applying policies and should revert to the vanilla state as it may be + * made visible again. + * + * The current implementation only resets the essential configurations. + * This needs to be expanded to cover all the visible parts. + */ +static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + mem_cgroup_resize_limit(memcg, ULLONG_MAX); + mem_cgroup_resize_memsw_limit(memcg, ULLONG_MAX); + memcg_update_kmem_limit(memcg, ULLONG_MAX); + res_counter_set_soft_limit(&memcg->res, ULLONG_MAX); +} + #ifdef CONFIG_MMU /* Handlers for move charge at task migration. */ -#define PRECHARGE_COUNT_AT_ONCE 256 static int mem_cgroup_do_precharge(unsigned long count) { - int ret = 0; - int batch_count = PRECHARGE_COUNT_AT_ONCE; - struct mem_cgroup *memcg = mc.to; + int ret; - if (mem_cgroup_is_root(memcg)) { + /* Try a single bulk charge without reclaim first */ + ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_WAIT, count); + if (!ret) { mc.precharge += count; - /* we don't need css_get for root */ return ret; } - /* try to charge at once */ - if (count > 1) { - struct res_counter *dummy; - /* - * "memcg" cannot be under rmdir() because we've already checked - * by cgroup_lock_live_cgroup() that it is not removed and we - * are still under the same cgroup_mutex. So we can postpone - * css_get(). - */ - if (res_counter_charge(&memcg->res, PAGE_SIZE * count, &dummy)) - goto one_by_one; - if (do_swap_account && res_counter_charge(&memcg->memsw, - PAGE_SIZE * count, &dummy)) { - res_counter_uncharge(&memcg->res, PAGE_SIZE * count); - goto one_by_one; - } - mc.precharge += count; + if (ret == -EINTR) { + cancel_charge(root_mem_cgroup, count); return ret; } -one_by_one: - /* fall back to one by one charge */ + + /* Try charges one by one with reclaim */ while (count--) { - if (signal_pending(current)) { - ret = -EINTR; - break; - } - if (!batch_count--) { - batch_count = PRECHARGE_COUNT_AT_ONCE; - cond_resched(); - } - ret = mem_cgroup_try_charge(memcg, GFP_KERNEL, 1, false); + ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1); + /* + * In case of failure, any residual charges against + * mc.to will be dropped by mem_cgroup_clear_mc() + * later on. However, cancel any charges that are + * bypassed to root right away or they'll be lost. + */ + if (ret == -EINTR) + cancel_charge(root_mem_cgroup, 1); if (ret) - /* mem_cgroup_clear_mc() will do uncharge later */ return ret; mc.precharge++; + cond_resched(); } - return ret; + return 0; } /** @@ -6725,9 +5828,9 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, if (page) { pc = lookup_page_cgroup(page); /* - * Do only loose check w/o page_cgroup lock. - * mem_cgroup_move_account() checks the pc is valid or not under - * the lock. + * Do only loose check w/o serialization. + * mem_cgroup_move_account() checks the pc is valid or + * not under LRU exclusion. */ if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) { ret = MC_TARGET_PAGE; @@ -6852,7 +5955,7 @@ static void __mem_cgroup_clear_mc(void) /* we must uncharge all the leftover precharges from mc.to */ if (mc.precharge) { - __mem_cgroup_cancel_charge(mc.to, mc.precharge); + cancel_charge(mc.to, mc.precharge); mc.precharge = 0; } /* @@ -6860,27 +5963,24 @@ static void __mem_cgroup_clear_mc(void) * we must uncharge here. */ if (mc.moved_charge) { - __mem_cgroup_cancel_charge(mc.from, 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)) - res_counter_uncharge(&mc.from->memsw, - PAGE_SIZE * mc.moved_swap); + res_counter_uncharge(&mc.from->memsw, + PAGE_SIZE * mc.moved_swap); for (i = 0; i < mc.moved_swap; i++) css_put(&mc.from->css); - if (!mem_cgroup_is_root(mc.to)) { - /* - * we charged both to->res and to->memsw, so we should - * uncharge to->res. - */ - res_counter_uncharge(&mc.to->res, - PAGE_SIZE * mc.moved_swap); - } + /* + * we charged both to->res and to->memsw, so we should + * uncharge to->res. + */ + res_counter_uncharge(&mc.to->res, + PAGE_SIZE * mc.moved_swap); /* we've already done css_get(mc.to) */ mc.moved_swap = 0; } @@ -7133,16 +6233,17 @@ static void mem_cgroup_move_task(struct cgroup_subsys_state *css, /* * Cgroup retains root cgroups across [un]mount cycles making it necessary - * to verify sane_behavior flag on each mount attempt. + * 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 with sane_behavior. cgroup core + * 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_sane_behavior(root_css->cgroup)) + if (cgroup_on_dfl(root_css->cgroup)) mem_cgroup_from_css(root_css)->use_hierarchy = true; } @@ -7151,11 +6252,12 @@ struct cgroup_subsys memory_cgrp_subsys = { .css_online = mem_cgroup_css_online, .css_offline = mem_cgroup_css_offline, .css_free = mem_cgroup_css_free, + .css_reset = mem_cgroup_css_reset, .can_attach = mem_cgroup_can_attach, .cancel_attach = mem_cgroup_cancel_attach, .attach = mem_cgroup_move_task, .bind = mem_cgroup_bind, - .base_cftypes = mem_cgroup_files, + .legacy_cftypes = mem_cgroup_files, .early_init = 0, }; @@ -7172,7 +6274,8 @@ __setup("swapaccount=", enable_swap_account); static void __init memsw_file_init(void) { - WARN_ON(cgroup_add_cftypes(&memory_cgrp_subsys, memsw_cgroup_files)); + WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, + memsw_cgroup_files)); } static void __init enable_swap_cgroup(void) @@ -7189,6 +6292,398 @@ static void __init enable_swap_cgroup(void) } #endif +#ifdef CONFIG_MEMCG_SWAP +/** + * 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 page_cgroup *pc; + unsigned short oldid; + + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(page_count(page), page); + + if (!do_swap_account) + return; + + pc = lookup_page_cgroup(page); + + /* Readahead page, never charged */ + if (!PageCgroupUsed(pc)) + return; + + VM_BUG_ON_PAGE(!(pc->flags & PCG_MEMSW), page); + + oldid = swap_cgroup_record(entry, mem_cgroup_id(pc->mem_cgroup)); + VM_BUG_ON_PAGE(oldid, page); + + pc->flags &= ~PCG_MEMSW; + css_get(&pc->mem_cgroup->css); + mem_cgroup_swap_statistics(pc->mem_cgroup, true); +} + +/** + * mem_cgroup_uncharge_swap - uncharge a swap entry + * @entry: swap entry to uncharge + * + * Drop the memsw charge associated with @entry. + */ +void mem_cgroup_uncharge_swap(swp_entry_t entry) +{ + struct mem_cgroup *memcg; + unsigned short id; + + if (!do_swap_account) + return; + + id = swap_cgroup_record(entry, 0); + rcu_read_lock(); + memcg = mem_cgroup_lookup(id); + if (memcg) { + res_counter_uncharge(&memcg->memsw, PAGE_SIZE); + mem_cgroup_swap_statistics(memcg, false); + css_put(&memcg->css); + } + rcu_read_unlock(); +} +#endif + +/** + * 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 + * + * 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) +{ + struct mem_cgroup *memcg = NULL; + unsigned int nr_pages = 1; + int ret = 0; + + if (mem_cgroup_disabled()) + goto out; + + if (PageSwapCache(page)) { + struct page_cgroup *pc = lookup_page_cgroup(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. + */ + if (PageCgroupUsed(pc)) + goto out; + } + + if (PageTransHuge(page)) { + nr_pages <<= compound_order(page); + VM_BUG_ON_PAGE(!PageTransHuge(page), page); + } + + if (do_swap_account && PageSwapCache(page)) + memcg = try_get_mem_cgroup_from_page(page); + if (!memcg) + memcg = get_mem_cgroup_from_mm(mm); + + ret = try_charge(memcg, gfp_mask, nr_pages); + + css_put(&memcg->css); + + if (ret == -EINTR) { + memcg = root_mem_cgroup; + ret = 0; + } +out: + *memcgp = memcg; + 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 + * + * 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. + * + * 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. + * + * Use mem_cgroup_cancel_charge() to cancel the transaction instead. + */ +void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, + bool lrucare) +{ + unsigned int nr_pages = 1; + + VM_BUG_ON_PAGE(!page->mapping, page); + VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); + + 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; + + commit_charge(page, memcg, lrucare); + + if (PageTransHuge(page)) { + nr_pages <<= compound_order(page); + VM_BUG_ON_PAGE(!PageTransHuge(page), page); + } + + local_irq_disable(); + mem_cgroup_charge_statistics(memcg, page, nr_pages); + memcg_check_events(memcg, page); + local_irq_enable(); + + if (do_swap_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); + } +} + +/** + * mem_cgroup_cancel_charge - cancel a page charge + * @page: page to charge + * @memcg: memcg to charge the page to + * + * Cancel a charge transaction started by mem_cgroup_try_charge(). + */ +void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) +{ + unsigned int nr_pages = 1; + + 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; + + if (PageTransHuge(page)) { + nr_pages <<= compound_order(page); + VM_BUG_ON_PAGE(!PageTransHuge(page), page); + } + + cancel_charge(memcg, nr_pages); +} + +static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout, + unsigned long nr_mem, unsigned long nr_memsw, + unsigned long nr_anon, unsigned long nr_file, + unsigned long nr_huge, struct page *dummy_page) +{ + unsigned long flags; + + if (nr_mem) + res_counter_uncharge(&memcg->res, nr_mem * PAGE_SIZE); + if (nr_memsw) + res_counter_uncharge(&memcg->memsw, nr_memsw * PAGE_SIZE); + + memcg_oom_recover(memcg); + + local_irq_save(flags); + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS], nr_anon); + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_file); + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], nr_huge); + __this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT], pgpgout); + __this_cpu_add(memcg->stat->nr_page_events, nr_anon + nr_file); + memcg_check_events(memcg, dummy_page); + local_irq_restore(flags); +} + +static void uncharge_list(struct list_head *page_list) +{ + struct mem_cgroup *memcg = NULL; + unsigned long nr_memsw = 0; + unsigned long nr_anon = 0; + unsigned long nr_file = 0; + unsigned long nr_huge = 0; + unsigned long pgpgout = 0; + unsigned long nr_mem = 0; + struct list_head *next; + struct page *page; + + next = page_list->next; + do { + unsigned int nr_pages = 1; + struct page_cgroup *pc; + + page = list_entry(next, struct page, lru); + next = page->lru.next; + + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(page_count(page), page); + + pc = lookup_page_cgroup(page); + if (!PageCgroupUsed(pc)) + continue; + + /* + * Nobody should be changing or seriously looking at + * pc->mem_cgroup and pc->flags at this point, we have + * fully exclusive access to the page. + */ + + if (memcg != pc->mem_cgroup) { + if (memcg) { + uncharge_batch(memcg, pgpgout, nr_mem, nr_memsw, + nr_anon, nr_file, nr_huge, page); + pgpgout = nr_mem = nr_memsw = 0; + nr_anon = nr_file = nr_huge = 0; + } + memcg = pc->mem_cgroup; + } + + if (PageTransHuge(page)) { + nr_pages <<= compound_order(page); + VM_BUG_ON_PAGE(!PageTransHuge(page), page); + nr_huge += nr_pages; + } + + if (PageAnon(page)) + nr_anon += nr_pages; + else + nr_file += nr_pages; + + if (pc->flags & PCG_MEM) + nr_mem += nr_pages; + if (pc->flags & PCG_MEMSW) + nr_memsw += nr_pages; + pc->flags = 0; + + pgpgout++; + } while (next != page_list); + + if (memcg) + uncharge_batch(memcg, pgpgout, nr_mem, nr_memsw, + nr_anon, nr_file, nr_huge, page); +} + +/** + * mem_cgroup_uncharge - uncharge a page + * @page: page to uncharge + * + * Uncharge a page previously charged with mem_cgroup_try_charge() and + * mem_cgroup_commit_charge(). + */ +void mem_cgroup_uncharge(struct page *page) +{ + struct page_cgroup *pc; + + if (mem_cgroup_disabled()) + return; + + /* Don't touch page->lru of any random page, pre-check: */ + pc = lookup_page_cgroup(page); + if (!PageCgroupUsed(pc)) + return; + + INIT_LIST_HEAD(&page->lru); + uncharge_list(&page->lru); +} + +/** + * 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()) + return; + + if (!list_empty(page_list)) + uncharge_list(page_list); +} + +/** + * mem_cgroup_migrate - migrate a charge to another page + * @oldpage: currently charged page + * @newpage: page to transfer the charge to + * @lrucare: both pages might be on the LRU already + * + * Migrate the charge from @oldpage to @newpage. + * + * Both pages must be locked, @newpage->mapping must be set up. + */ +void mem_cgroup_migrate(struct page *oldpage, struct page *newpage, + bool lrucare) +{ + struct page_cgroup *pc; + int isolated; + + VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); + VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); + VM_BUG_ON_PAGE(!lrucare && PageLRU(oldpage), oldpage); + VM_BUG_ON_PAGE(!lrucare && PageLRU(newpage), newpage); + VM_BUG_ON_PAGE(PageAnon(oldpage) != PageAnon(newpage), newpage); + VM_BUG_ON_PAGE(PageTransHuge(oldpage) != PageTransHuge(newpage), + newpage); + + if (mem_cgroup_disabled()) + return; + + /* Page cache replacement: new page already charged? */ + pc = lookup_page_cgroup(newpage); + if (PageCgroupUsed(pc)) + return; + + /* Re-entrant migration: old page already uncharged? */ + pc = lookup_page_cgroup(oldpage); + if (!PageCgroupUsed(pc)) + return; + + VM_BUG_ON_PAGE(!(pc->flags & PCG_MEM), oldpage); + VM_BUG_ON_PAGE(do_swap_account && !(pc->flags & PCG_MEMSW), oldpage); + + if (lrucare) + lock_page_lru(oldpage, &isolated); + + pc->flags = 0; + + if (lrucare) + unlock_page_lru(oldpage, isolated); + + commit_charge(newpage, pc->mem_cgroup, lrucare); +} + /* * subsys_initcall() for memory controller. * |
