diff options
Diffstat (limited to 'mm/memcontrol.c')
| -rw-r--r-- | mm/memcontrol.c | 2022 |
1 files changed, 786 insertions, 1236 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f009a14918d2..d6ac0e33e150 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -292,6 +292,9 @@ struct mem_cgroup { /* vmpressure notifications */ struct vmpressure vmpressure; + /* css_online() has been completed */ + int initialized; + /* * the counter to account for mem+swap usage. */ @@ -315,9 +318,6 @@ struct mem_cgroup { /* OOM-Killer disable */ int oom_kill_disable; - /* set when res.limit == memsw.limit */ - bool memsw_is_minimum; - /* protect arrays of thresholds */ struct mutex thresholds_lock; @@ -481,14 +481,6 @@ enum res_type { #define OOM_CONTROL (0) /* - * Reclaim flags for mem_cgroup_hierarchical_reclaim - */ -#define MEM_CGROUP_RECLAIM_NOSWAP_BIT 0x0 -#define MEM_CGROUP_RECLAIM_NOSWAP (1 << MEM_CGROUP_RECLAIM_NOSWAP_BIT) -#define MEM_CGROUP_RECLAIM_SHRINK_BIT 0x1 -#define MEM_CGROUP_RECLAIM_SHRINK (1 << MEM_CGROUP_RECLAIM_SHRINK_BIT) - -/* * The memcg_create_mutex will be held whenever a new cgroup is created. * As a consequence, any change that needs to protect against new child cgroups * appearing has to hold it as well. @@ -646,11 +638,13 @@ int memcg_limited_groups_array_size; struct static_key memcg_kmem_enabled_key; EXPORT_SYMBOL(memcg_kmem_enabled_key); +static void memcg_free_cache_id(int id); + static void disarm_kmem_keys(struct mem_cgroup *memcg) { if (memcg_kmem_is_active(memcg)) { static_key_slow_dec(&memcg_kmem_enabled_key); - ida_simple_remove(&kmem_limited_groups, memcg->kmemcg_id); + memcg_free_cache_id(memcg->kmemcg_id); } /* * This check can't live in kmem destruction function, @@ -754,9 +748,11 @@ static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz, struct mem_cgroup_tree_per_zone *mctz) { - spin_lock(&mctz->lock); + unsigned long flags; + + spin_lock_irqsave(&mctz->lock, flags); __mem_cgroup_remove_exceeded(mz, mctz); - spin_unlock(&mctz->lock); + spin_unlock_irqrestore(&mctz->lock, flags); } @@ -779,7 +775,9 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) * 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(mz, mctz); @@ -788,7 +786,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) * If excess is 0, no tree ops. */ __mem_cgroup_insert_exceeded(mz, mctz, excess); - spin_unlock(&mctz->lock); + spin_unlock_irqrestore(&mctz->lock, flags); } } } @@ -839,9 +837,9 @@ 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; } @@ -882,13 +880,6 @@ 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) { @@ -909,13 +900,13 @@ 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 @@ -1013,7 +1004,6 @@ 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))) { @@ -1026,8 +1016,6 @@ 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); @@ -1035,8 +1023,7 @@ 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) @@ -1106,10 +1093,21 @@ skip_node: * skipping css reference should be safe. */ if (next_css) { - if ((next_css == &root->css) || - ((next_css->flags & CSS_ONLINE) && - css_tryget_online(next_css))) - return mem_cgroup_from_css(next_css); + struct mem_cgroup *memcg = mem_cgroup_from_css(next_css); + + if (next_css == &root->css) + return memcg; + + if (css_tryget_online(next_css)) { + /* + * Make sure the memcg is initialized: + * mem_cgroup_css_online() orders the the + * initialization against setting the flag. + */ + if (smp_load_acquire(&memcg->initialized)) + return memcg; + css_put(next_css); + } prev_css = next_css; goto skip_node; @@ -1347,20 +1345,6 @@ 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 @@ -1552,12 +1536,8 @@ int mem_cgroup_swappiness(struct mem_cgroup *memcg) * start move here. */ -/* for quick checking without looking up memcg */ -atomic_t memcg_moving __read_mostly; - static void mem_cgroup_start_move(struct mem_cgroup *memcg) { - atomic_inc(&memcg_moving); atomic_inc(&memcg->moving_account); synchronize_rcu(); } @@ -1568,10 +1548,8 @@ static void mem_cgroup_end_move(struct mem_cgroup *memcg) * Now, mem_cgroup_clear_mc() may call this function with NULL. * We check NULL in callee rather than caller. */ - if (memcg) { - atomic_dec(&memcg_moving); + if (memcg) atomic_dec(&memcg->moving_account); - } } /* @@ -1813,42 +1791,6 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, NULL, "Memory cgroup out of memory"); } -static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg, - gfp_t gfp_mask, - unsigned long flags) -{ - unsigned long total = 0; - bool noswap = false; - int loop; - - if (flags & MEM_CGROUP_RECLAIM_NOSWAP) - noswap = true; - if (!(flags & MEM_CGROUP_RECLAIM_SHRINK) && memcg->memsw_is_minimum) - noswap = true; - - for (loop = 0; loop < MEM_CGROUP_MAX_RECLAIM_LOOPS; loop++) { - if (loop) - drain_all_stock_async(memcg); - total += try_to_free_mem_cgroup_pages(memcg, gfp_mask, noswap); - /* - * Allow limit shrinkers, which are triggered directly - * by userspace, to catch signals and stop reclaim - * after minimal progress, regardless of the margin. - */ - if (total && (flags & MEM_CGROUP_RECLAIM_SHRINK)) - break; - if (mem_cgroup_margin(memcg)) - break; - /* - * If nothing was reclaimed after two attempts, there - * may be no reclaimable pages in this hierarchy. - */ - if (loop && !total) - break; - } - return total; -} - /** * test_mem_cgroup_node_reclaimable * @memcg: the target memcg @@ -2256,49 +2198,52 @@ cleanup: return true; } -/* - * Used to update mapped file or writeback or other statistics. - * - * Notes: Race condition +/** + * mem_cgroup_begin_page_stat - begin a page state statistics transaction + * @page: page that is going to change accounted state + * @locked: &memcg->move_lock slowpath was taken + * @flags: IRQ-state flags for &memcg->move_lock * - * We usually use lock_page_cgroup() for accessing page_cgroup member but - * it tends to be costly. But considering some conditions, we doesn't need - * to do so _always_. + * This function must mark the beginning of an accounted page state + * change to prevent double accounting when the page is concurrently + * being moved to another memcg: * - * 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". + * memcg = mem_cgroup_begin_page_stat(page, &locked, &flags); + * if (TestClearPageState(page)) + * mem_cgroup_update_page_stat(memcg, state, -1); + * mem_cgroup_end_page_stat(memcg, locked, flags); * - * 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. + * The RCU lock is held throughout the transaction. The fast path can + * get away without acquiring the memcg->move_lock (@locked is false) + * because page moving starts with an RCU grace period. * - * Considering "move", this is an only case we see a race. To make the race - * small, we check memcg->moving_account and detect there are possibility - * of race or not. If there is, we take a lock. + * The RCU lock also protects the memcg from being freed when the page + * state that is going to change is the only thing preventing the page + * from being uncharged. E.g. end-writeback clearing PageWriteback(), + * which allows migration to go ahead and uncharge the page before the + * account transaction might be complete. */ - -void __mem_cgroup_begin_update_page_stat(struct page *page, - bool *locked, unsigned long *flags) +struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, + bool *locked, + unsigned long *flags) { struct mem_cgroup *memcg; struct page_cgroup *pc; + rcu_read_lock(); + + if (mem_cgroup_disabled()) + return NULL; + pc = lookup_page_cgroup(page); again: memcg = pc->mem_cgroup; if (unlikely(!memcg || !PageCgroupUsed(pc))) - return; - /* - * 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(). - */ - VM_BUG_ON(!rcu_read_lock_held()); + return NULL; + + *locked = false; if (atomic_read(&memcg->moving_account) <= 0) - return; + return memcg; move_lock_mem_cgroup(memcg, flags); if (memcg != pc->mem_cgroup || !PageCgroupUsed(pc)) { @@ -2306,36 +2251,40 @@ again: goto again; } *locked = true; + + return memcg; } -void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags) +/** + * mem_cgroup_end_page_stat - finish a page state statistics transaction + * @memcg: the memcg that was accounted against + * @locked: value received from mem_cgroup_begin_page_stat() + * @flags: value received from mem_cgroup_begin_page_stat() + */ +void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool locked, + unsigned long flags) { - struct page_cgroup *pc = lookup_page_cgroup(page); + if (memcg && locked) + move_unlock_mem_cgroup(memcg, &flags); - /* - * It's guaranteed that pc->mem_cgroup never changes while - * lock is held because a routine modifies pc->mem_cgroup - * should take move_lock_mem_cgroup(). - */ - move_unlock_mem_cgroup(pc->mem_cgroup, flags); + rcu_read_unlock(); } -void mem_cgroup_update_page_stat(struct page *page, +/** + * mem_cgroup_update_page_stat - update page state statistics + * @memcg: memcg to account against + * @idx: page state item to account + * @val: number of pages (positive or negative) + * + * See mem_cgroup_begin_page_stat() for locking requirements. + */ +void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx, int val) { - struct mem_cgroup *memcg; - struct page_cgroup *pc = lookup_page_cgroup(page); - unsigned long uninitialized_var(flags); - - if (mem_cgroup_disabled()) - return; - VM_BUG_ON(!rcu_read_lock_held()); - memcg = pc->mem_cgroup; - if (unlikely(!memcg || !PageCgroupUsed(pc))) - return; - this_cpu_add(memcg->stat->count[idx], val); + if (memcg) + this_cpu_add(memcg->stat->count[idx], val); } /* @@ -2551,55 +2500,74 @@ 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 flags = 0; - int ret; - - ret = res_counter_charge(&memcg->res, csize, &fail_res); + unsigned long nr_reclaimed; + unsigned long long size; + bool may_swap = true; + bool drained = false; + int ret = 0; - if (likely(!ret)) { - if (!do_swap_account) - return CHARGE_OK; - ret = res_counter_charge(&memcg->memsw, csize, &fail_res); - if (likely(!ret)) - return CHARGE_OK; + if (mem_cgroup_is_root(memcg)) + goto done; +retry: + if (consume_stock(memcg, nr_pages)) + goto done; - res_counter_uncharge(&memcg->res, csize); - mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw); - flags |= MEM_CGROUP_RECLAIM_NOSWAP; - } else + size = batch * PAGE_SIZE; + if (!do_swap_account || + !res_counter_charge(&memcg->memsw, size, &fail_res)) { + if (!res_counter_charge(&memcg->res, size, &fail_res)) + goto done_restock; + if (do_swap_account) + res_counter_uncharge(&memcg->memsw, size); mem_over_limit = mem_cgroup_from_res_counter(fail_res, res); + } else { + mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw); + may_swap = false; + } + + 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 = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, + gfp_mask, may_swap); - 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 (!drained) { + drain_all_stock_async(mem_over_limit); + drained = true; + 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 @@ -2609,142 +2577,48 @@ 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) || - current->flags & PF_EXITING)) - 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; -} - -/** - * 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); - } + if (mem_cgroup_is_root(memcg)) + return; + + res_counter_uncharge(&memcg->res, bytes); + if (do_swap_account) + res_counter_uncharge(&memcg->memsw, bytes); } /* @@ -2779,6 +2653,16 @@ 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; @@ -2789,7 +2673,6 @@ 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_online(&memcg->css)) @@ -2803,23 +2686,46 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) 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 @@ -2830,52 +2736,28 @@ 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); @@ -2889,12 +2771,6 @@ static DEFINE_MUTEX(memcg_slab_mutex); static DEFINE_MUTEX(activate_kmem_mutex); -static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg) -{ - return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg) && - memcg_kmem_is_active(memcg); -} - /* * This is a bit cumbersome, but it is rarely used and avoids a backpointer * in the memcg_cache_params struct. @@ -2914,7 +2790,7 @@ static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v) struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); struct memcg_cache_params *params; - if (!memcg_can_account_kmem(memcg)) + if (!memcg_kmem_is_active(memcg)) return -EIO; print_slabinfo_header(m); @@ -2937,22 +2813,21 @@ 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); @@ -2998,19 +2873,44 @@ int memcg_cache_id(struct mem_cgroup *memcg) return memcg ? memcg->kmemcg_id : -1; } -static size_t memcg_caches_array_size(int num_groups) +static int memcg_alloc_cache_id(void) { - ssize_t size; - if (num_groups <= 0) - return 0; + int id, size; + int err; - size = 2 * num_groups; + id = ida_simple_get(&kmem_limited_groups, + 0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL); + if (id < 0) + return id; + + if (id < memcg_limited_groups_array_size) + return id; + + /* + * There's no space for the new id in memcg_caches arrays, + * so we have to grow them. + */ + + size = 2 * (id + 1); if (size < MEMCG_CACHES_MIN_SIZE) size = MEMCG_CACHES_MIN_SIZE; else if (size > MEMCG_CACHES_MAX_SIZE) size = MEMCG_CACHES_MAX_SIZE; - return size; + mutex_lock(&memcg_slab_mutex); + err = memcg_update_all_caches(size); + mutex_unlock(&memcg_slab_mutex); + + if (err) { + ida_simple_remove(&kmem_limited_groups, id); + return err; + } + return id; +} + +static void memcg_free_cache_id(int id) +{ + ida_simple_remove(&kmem_limited_groups, id); } /* @@ -3020,97 +2920,7 @@ static size_t memcg_caches_array_size(int num_groups) */ void memcg_update_array_size(int num) { - if (num > memcg_limited_groups_array_size) - memcg_limited_groups_array_size = memcg_caches_array_size(num); -} - -int memcg_update_cache_size(struct kmem_cache *s, int num_groups) -{ - struct memcg_cache_params *cur_params = s->memcg_params; - - VM_BUG_ON(!is_root_cache(s)); - - if (num_groups > memcg_limited_groups_array_size) { - int i; - struct memcg_cache_params *new_params; - ssize_t size = memcg_caches_array_size(num_groups); - - size *= sizeof(void *); - size += offsetof(struct memcg_cache_params, memcg_caches); - - new_params = kzalloc(size, GFP_KERNEL); - if (!new_params) - return -ENOMEM; - - new_params->is_root_cache = true; - - /* - * There is the chance it will be bigger than - * memcg_limited_groups_array_size, if we failed an allocation - * in a cache, in which case all caches updated before it, will - * have a bigger array. - * - * But if that is the case, the data after - * memcg_limited_groups_array_size is certainly unused - */ - for (i = 0; i < memcg_limited_groups_array_size; i++) { - if (!cur_params->memcg_caches[i]) - continue; - new_params->memcg_caches[i] = - cur_params->memcg_caches[i]; - } - - /* - * Ideally, we would wait until all caches succeed, and only - * then free the old one. But this is not worth the extra - * pointer per-cache we'd have to have for this. - * - * It is not a big deal if some caches are left with a size - * bigger than the others. And all updates will reset this - * anyway. - */ - rcu_assign_pointer(s->memcg_params, new_params); - if (cur_params) - kfree_rcu(cur_params, rcu_head); - } - return 0; -} - -int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, - struct kmem_cache *root_cache) -{ - size_t size; - - if (!memcg_kmem_enabled()) - return 0; - - if (!memcg) { - size = offsetof(struct memcg_cache_params, memcg_caches); - size += memcg_limited_groups_array_size * sizeof(void *); - } else - size = sizeof(struct memcg_cache_params); - - s->memcg_params = kzalloc(size, GFP_KERNEL); - if (!s->memcg_params) - return -ENOMEM; - - if (memcg) { - s->memcg_params->memcg = memcg; - s->memcg_params->root_cache = root_cache; - css_get(&memcg->css); - } else - s->memcg_params->is_root_cache = true; - - return 0; -} - -void memcg_free_cache_params(struct kmem_cache *s) -{ - if (!s->memcg_params) - return; - if (!s->memcg_params->is_root_cache) - css_put(&s->memcg_params->memcg->css); - kfree(s->memcg_params); + memcg_limited_groups_array_size = num; } static void memcg_register_cache(struct mem_cgroup *memcg, @@ -3143,6 +2953,7 @@ static void memcg_register_cache(struct mem_cgroup *memcg, if (!cachep) return; + css_get(&memcg->css); list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches); /* @@ -3176,6 +2987,9 @@ static void memcg_unregister_cache(struct kmem_cache *cachep) list_del(&cachep->memcg_params->list); kmem_cache_destroy(cachep); + + /* drop the reference taken in memcg_register_cache */ + css_put(&memcg->css); } /* @@ -3353,7 +3167,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(current->mm->owner)); - if (!memcg_can_account_kmem(memcg)) + if (!memcg_kmem_is_active(memcg)) goto out; memcg_cachep = cache_from_memcg_idx(cachep, memcg_cache_id(memcg)); @@ -3438,7 +3252,7 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order) memcg = get_mem_cgroup_from_mm(current->mm); - if (!memcg_can_account_kmem(memcg)) { + if (!memcg_kmem_is_active(memcg)) { css_put(&memcg->css); return true; } @@ -3463,12 +3277,13 @@ 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) @@ -3478,19 +3293,11 @@ 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 @@ -3510,7 +3317,6 @@ static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg) #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. @@ -3531,8 +3337,7 @@ 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); @@ -3562,7 +3367,6 @@ 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); @@ -3576,15 +3380,21 @@ 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], @@ -3598,20 +3408,25 @@ 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; } @@ -3682,456 +3497,12 @@ 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_online(). - */ - 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); } /** @@ -4183,175 +3554,6 @@ 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) { @@ -4392,7 +3594,6 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val) { int retry_count; - u64 memswlimit, memlimit; int ret = 0; int children = mem_cgroup_count_children(memcg); u64 curusage, oldusage; @@ -4419,31 +3620,23 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, * We have to guarantee memcg->res.limit <= memcg->memsw.limit. */ mutex_lock(&set_limit_mutex); - memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT); - if (memswlimit < val) { + if (res_counter_read_u64(&memcg->memsw, RES_LIMIT) < val) { ret = -EINVAL; mutex_unlock(&set_limit_mutex); break; } - memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT); - if (memlimit < val) + if (res_counter_read_u64(&memcg->res, RES_LIMIT) < val) enlarge = 1; ret = res_counter_set_limit(&memcg->res, val); - if (!ret) { - if (memswlimit == val) - memcg->memsw_is_minimum = true; - else - memcg->memsw_is_minimum = false; - } mutex_unlock(&set_limit_mutex); if (!ret) break; - mem_cgroup_reclaim(memcg, GFP_KERNEL, - MEM_CGROUP_RECLAIM_SHRINK); + try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, true); + curusage = res_counter_read_u64(&memcg->res, RES_USAGE); /* Usage is reduced ? */ if (curusage >= oldusage) @@ -4461,7 +3654,7 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, unsigned long long val) { int retry_count; - u64 memlimit, memswlimit, oldusage, curusage; + u64 oldusage, curusage; int children = mem_cgroup_count_children(memcg); int ret = -EBUSY; int enlarge = 0; @@ -4480,30 +3673,21 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, * We have to guarantee memcg->res.limit <= memcg->memsw.limit. */ mutex_lock(&set_limit_mutex); - memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT); - if (memlimit > val) { + if (res_counter_read_u64(&memcg->res, RES_LIMIT) > val) { ret = -EINVAL; mutex_unlock(&set_limit_mutex); break; } - memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT); - if (memswlimit < val) + if (res_counter_read_u64(&memcg->memsw, RES_LIMIT) < val) enlarge = 1; ret = res_counter_set_limit(&memcg->memsw, val); - if (!ret) { - if (memlimit == val) - memcg->memsw_is_minimum = true; - else - memcg->memsw_is_minimum = false; - } mutex_unlock(&set_limit_mutex); if (!ret) break; - mem_cgroup_reclaim(memcg, GFP_KERNEL, - MEM_CGROUP_RECLAIM_NOSWAP | - MEM_CGROUP_RECLAIM_SHRINK); + try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, false); + curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); /* Usage is reduced ? */ if (curusage >= oldusage) @@ -4550,7 +3734,7 @@ 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 @@ -4590,7 +3774,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, */ /* If excess == 0, no tree ops */ __mem_cgroup_insert_exceeded(mz, mctz, excess); - spin_unlock(&mctz->lock); + spin_unlock_irq(&mctz->lock); css_put(&mz->memcg->css); loop++; /* @@ -4752,8 +3936,8 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) if (signal_pending(current)) return -EINTR; - progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL, - false); + progress = try_to_free_mem_cgroup_pages(memcg, 1, + GFP_KERNEL, true); if (!progress) { nr_retries--; /* maybe some writeback is necessary */ @@ -4817,7 +4001,6 @@ out: return retval; } - static unsigned long mem_cgroup_recursive_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) { @@ -4857,38 +4040,29 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool 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 mem_cgroup_usage(memcg, false); + 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 mem_cgroup_usage(memcg, true); + 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 @@ -4928,23 +4102,12 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg, if (err) goto out; - memcg_id = ida_simple_get(&kmem_limited_groups, - 0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL); + memcg_id = memcg_alloc_cache_id(); if (memcg_id < 0) { err = memcg_id; goto out; } - /* - * 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); @@ -4965,10 +4128,6 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg, out: memcg_resume_kmem_account(); return err; - -out_rmid: - ida_simple_remove(&kmem_limited_groups, memcg_id); - goto out; } static int memcg_activate_kmem(struct mem_cgroup *memcg, @@ -5446,15 +4605,15 @@ 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 = mem_cgroup_usage(memcg, false); + } else if (type == _MEMSWAP) { thresholds = &memcg->memsw_thresholds; - else + usage = mem_cgroup_usage(memcg, true); + } 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); @@ -5534,18 +4693,19 @@ 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 = mem_cgroup_usage(memcg, false); + } else if (type == _MEMSWAP) { thresholds = &memcg->memsw_thresholds; - else + usage = mem_cgroup_usage(memcg, true); + } 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); @@ -6276,6 +5436,7 @@ 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); + int ret; if (css->id > MEM_CGROUP_ID_MAX) return -ENOSPC; @@ -6312,7 +5473,18 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) } mutex_unlock(&memcg_create_mutex); - return memcg_init_kmem(memcg, &memory_cgrp_subsys); + ret = memcg_init_kmem(memcg, &memory_cgrp_subsys); + if (ret) + return ret; + + /* + * Make sure the memcg is initialized: mem_cgroup_iter() + * orders reading memcg->initialized against its callers + * reading the memcg members. + */ + smp_store_release(&memcg->initialized, 1); + + return 0; } /* @@ -6435,55 +5607,38 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) #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; } /** @@ -6619,9 +5774,9 @@ 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; @@ -6746,7 +5901,7 @@ 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; } /* @@ -6754,7 +5909,7 @@ 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 */ @@ -6762,19 +5917,18 @@ static void __mem_cgroup_clear_mc(void) /* 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); + 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. - */ + /* + * we charged both to->res and to->memsw, so we should + * uncharge to->res. + */ + if (!mem_cgroup_is_root(mc.to)) res_counter_uncharge(&mc.to->res, - PAGE_SIZE * mc.moved_swap); - } + PAGE_SIZE * mc.moved_swap); /* we've already done css_get(mc.to) */ mc.moved_swap = 0; } @@ -7086,6 +6240,402 @@ 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) { + 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(); +} +#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 (!mem_cgroup_is_root(memcg)) { + 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. * |