X-Git-Url: http://git.monstr.eu/?a=blobdiff_plain;f=mm%2Fmemcontrol.c;h=7a4bd8b9adc213fdd21da52e6842c036b1c4c81a;hb=4b13f64de25686583db3e359b1b8e59049278b50;hp=d09776cd6e1041d896aa25e726d55f93e46581ed;hpb=e79220db6349344b6e770f0cae7e26d8636c1440;p=linux-2.6-microblaze.git diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d09776cd6e10..e6043ab3017c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -334,7 +334,7 @@ static int memcg_expand_one_shrinker_map(struct mem_cgroup *memcg, if (!old) return 0; - new = kvmalloc(sizeof(*new) + size, GFP_KERNEL); + new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid); if (!new) return -ENOMEM; @@ -378,7 +378,7 @@ static int memcg_alloc_shrinker_maps(struct mem_cgroup *memcg) mutex_lock(&memcg_shrinker_map_mutex); size = memcg_shrinker_map_size; for_each_node(nid) { - map = kvzalloc(sizeof(*map) + size, GFP_KERNEL); + map = kvzalloc_node(sizeof(*map) + size, GFP_KERNEL, nid); if (!map) { memcg_free_shrinker_maps(memcg); ret = -ENOMEM; @@ -759,13 +759,12 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) { - struct page *page = virt_to_head_page(p); - pg_data_t *pgdat = page_pgdat(page); + pg_data_t *pgdat = page_pgdat(virt_to_page(p)); struct mem_cgroup *memcg; struct lruvec *lruvec; rcu_read_lock(); - memcg = memcg_from_slab_page(page); + memcg = mem_cgroup_from_obj(p); /* Untracked pages have no memcg, no lruvec. Update only the node */ if (!memcg || memcg == root_mem_cgroup) { @@ -777,6 +776,17 @@ void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) rcu_read_unlock(); } +void mod_memcg_obj_state(void *p, int idx, int val) +{ + struct mem_cgroup *memcg; + + rcu_read_lock(); + memcg = mem_cgroup_from_obj(p); + if (memcg) + mod_memcg_state(memcg, idx, val); + rcu_read_unlock(); +} + /** * __count_memcg_events - account VM events in a cgroup * @memcg: the memory cgroup @@ -2297,28 +2307,41 @@ static void high_work_func(struct work_struct *work) #define MEMCG_DELAY_SCALING_SHIFT 14 /* - * Scheduled by try_charge() to be executed from the userland return path - * and reclaims memory over the high limit. + * Get the number of jiffies that we should penalise a mischievous cgroup which + * is exceeding its memory.high by checking both it and its ancestors. */ -void mem_cgroup_handle_over_high(void) +static unsigned long calculate_high_delay(struct mem_cgroup *memcg, + unsigned int nr_pages) { - unsigned long usage, high, clamped_high; - unsigned long pflags; - unsigned long penalty_jiffies, overage; - unsigned int nr_pages = current->memcg_nr_pages_over_high; - struct mem_cgroup *memcg; + unsigned long penalty_jiffies; + u64 max_overage = 0; - if (likely(!nr_pages)) - return; + do { + unsigned long usage, high; + u64 overage; - memcg = get_mem_cgroup_from_mm(current->mm); - reclaim_high(memcg, nr_pages, GFP_KERNEL); - current->memcg_nr_pages_over_high = 0; + usage = page_counter_read(&memcg->memory); + high = READ_ONCE(memcg->high); + + /* + * Prevent division by 0 in overage calculation by acting as if + * it was a threshold of 1 page + */ + high = max(high, 1UL); + + overage = usage - high; + overage <<= MEMCG_DELAY_PRECISION_SHIFT; + overage = div64_u64(overage, high); + + if (overage > max_overage) + max_overage = overage; + } while ((memcg = parent_mem_cgroup(memcg)) && + !mem_cgroup_is_root(memcg)); + + if (!max_overage) + return 0; /* - * memory.high is breached and reclaim is unable to keep up. Throttle - * allocators proactively to slow down excessive growth. - * * We use overage compared to memory.high to calculate the number of * jiffies to sleep (penalty_jiffies). Ideally this value should be * fairly lenient on small overages, and increasingly harsh when the @@ -2326,24 +2349,9 @@ void mem_cgroup_handle_over_high(void) * its crazy behaviour, so we exponentially increase the delay based on * overage amount. */ - - usage = page_counter_read(&memcg->memory); - high = READ_ONCE(memcg->high); - - if (usage <= high) - goto out; - - /* - * Prevent division by 0 in overage calculation by acting as if it was a - * threshold of 1 page - */ - clamped_high = max(high, 1UL); - - overage = div_u64((u64)(usage - high) << MEMCG_DELAY_PRECISION_SHIFT, - clamped_high); - - penalty_jiffies = ((u64)overage * overage * HZ) - >> (MEMCG_DELAY_PRECISION_SHIFT + MEMCG_DELAY_SCALING_SHIFT); + penalty_jiffies = max_overage * max_overage * HZ; + penalty_jiffies >>= MEMCG_DELAY_PRECISION_SHIFT; + penalty_jiffies >>= MEMCG_DELAY_SCALING_SHIFT; /* * Factor in the task's own contribution to the overage, such that four @@ -2360,7 +2368,32 @@ void mem_cgroup_handle_over_high(void) * application moving forwards and also permit diagnostics, albeit * extremely slowly. */ - penalty_jiffies = min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES); + return min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES); +} + +/* + * Scheduled by try_charge() to be executed from the userland return path + * and reclaims memory over the high limit. + */ +void mem_cgroup_handle_over_high(void) +{ + unsigned long penalty_jiffies; + unsigned long pflags; + unsigned int nr_pages = current->memcg_nr_pages_over_high; + struct mem_cgroup *memcg; + + if (likely(!nr_pages)) + return; + + memcg = get_mem_cgroup_from_mm(current->mm); + reclaim_high(memcg, nr_pages, GFP_KERNEL); + current->memcg_nr_pages_over_high = 0; + + /* + * memory.high is breached and reclaim is unable to keep up. Throttle + * allocators proactively to slow down excessive growth. + */ + penalty_jiffies = calculate_high_delay(memcg, nr_pages); /* * Don't sleep if the amount of jiffies this memcg owes us is so low @@ -2638,6 +2671,33 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg, } #ifdef CONFIG_MEMCG_KMEM +/* + * Returns a pointer to the memory cgroup to which the kernel object is charged. + * + * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(), + * cgroup_mutex, etc. + */ +struct mem_cgroup *mem_cgroup_from_obj(void *p) +{ + struct page *page; + + if (mem_cgroup_disabled()) + return NULL; + + page = virt_to_head_page(p); + + /* + * Slab pages don't have page->mem_cgroup set because corresponding + * kmem caches can be reparented during the lifetime. That's why + * memcg_from_slab_page() should be used instead. + */ + if (PageSlab(page)) + return memcg_from_slab_page(page); + + /* All other pages use page->mem_cgroup */ + return page->mem_cgroup; +} + static int memcg_alloc_cache_id(void) { int id, size; @@ -2821,18 +2881,16 @@ void memcg_kmem_put_cache(struct kmem_cache *cachep) } /** - * __memcg_kmem_charge_memcg: charge a kmem page - * @page: page to charge - * @gfp: reclaim mode - * @order: allocation order + * __memcg_kmem_charge: charge a number of kernel pages to a memcg * @memcg: memory cgroup to charge + * @gfp: reclaim mode + * @nr_pages: number of pages to charge * * Returns 0 on success, an error code on failure. */ -int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, - struct mem_cgroup *memcg) +int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, + unsigned int nr_pages) { - unsigned int nr_pages = 1 << order; struct page_counter *counter; int ret; @@ -2859,14 +2917,29 @@ int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, } /** - * __memcg_kmem_charge: charge a kmem page to the current memory cgroup + * __memcg_kmem_uncharge: uncharge a number of kernel pages from a memcg + * @memcg: memcg to uncharge + * @nr_pages: number of pages to uncharge + */ +void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages) +{ + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + page_counter_uncharge(&memcg->kmem, nr_pages); + + page_counter_uncharge(&memcg->memory, nr_pages); + if (do_memsw_account()) + page_counter_uncharge(&memcg->memsw, nr_pages); +} + +/** + * __memcg_kmem_charge_page: charge a kmem page to the current memory cgroup * @page: page to charge * @gfp: reclaim mode * @order: allocation order * * Returns 0 on success, an error code on failure. */ -int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order) +int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { struct mem_cgroup *memcg; int ret = 0; @@ -2876,7 +2949,7 @@ int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order) memcg = get_mem_cgroup_from_current(); if (!mem_cgroup_is_root(memcg)) { - ret = __memcg_kmem_charge_memcg(page, gfp, order, memcg); + ret = __memcg_kmem_charge(memcg, gfp, 1 << order); if (!ret) { page->mem_cgroup = memcg; __SetPageKmemcg(page); @@ -2887,26 +2960,11 @@ int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order) } /** - * __memcg_kmem_uncharge_memcg: uncharge a kmem page - * @memcg: memcg to uncharge - * @nr_pages: number of pages to uncharge - */ -void __memcg_kmem_uncharge_memcg(struct mem_cgroup *memcg, - unsigned int nr_pages) -{ - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) - page_counter_uncharge(&memcg->kmem, nr_pages); - - page_counter_uncharge(&memcg->memory, nr_pages); - if (do_memsw_account()) - page_counter_uncharge(&memcg->memsw, nr_pages); -} -/** - * __memcg_kmem_uncharge: uncharge a kmem page + * __memcg_kmem_uncharge_page: uncharge a kmem page * @page: page to uncharge * @order: allocation order */ -void __memcg_kmem_uncharge(struct page *page, int order) +void __memcg_kmem_uncharge_page(struct page *page, int order) { struct mem_cgroup *memcg = page->mem_cgroup; unsigned int nr_pages = 1 << order; @@ -2915,7 +2973,7 @@ void __memcg_kmem_uncharge(struct page *page, int order) return; VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page); - __memcg_kmem_uncharge_memcg(memcg, nr_pages); + __memcg_kmem_uncharge(memcg, nr_pages); page->mem_cgroup = NULL; /* slab pages do not have PageKmemcg flag set */ @@ -4027,7 +4085,7 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, struct mem_cgroup_thresholds *thresholds; struct mem_cgroup_threshold_ary *new; unsigned long usage; - int i, j, size; + int i, j, size, entries; mutex_lock(&memcg->thresholds_lock); @@ -4047,14 +4105,20 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, __mem_cgroup_threshold(memcg, type == _MEMSWAP); /* Calculate new number of threshold */ - size = 0; + size = entries = 0; for (i = 0; i < thresholds->primary->size; i++) { if (thresholds->primary->entries[i].eventfd != eventfd) size++; + else + entries++; } new = thresholds->spare; + /* If no items related to eventfd have been cleared, nothing to do */ + if (!entries) + goto unlock; + /* Set thresholds array to NULL if we don't have thresholds */ if (!size) { kfree(new); @@ -4725,7 +4789,8 @@ static struct cftype mem_cgroup_legacy_files[] = { .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, -#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG) +#if defined(CONFIG_MEMCG_KMEM) && \ + (defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)) { .name = "kmem.slabinfo", .seq_start = memcg_slab_start, @@ -6682,19 +6747,9 @@ void mem_cgroup_sk_alloc(struct sock *sk) if (!mem_cgroup_sockets_enabled) return; - /* - * Socket cloning can throw us here with sk_memcg already - * filled. It won't however, necessarily happen from - * process context. So the test for root memcg given - * the current task's memcg won't help us in this case. - * - * Respecting the original socket's memcg is a better - * decision in this case. - */ - if (sk->sk_memcg) { - css_get(&sk->sk_memcg->css); + /* Do not associate the sock with unrelated interrupted task's memcg. */ + if (in_interrupt()) return; - } rcu_read_lock(); memcg = mem_cgroup_from_task(current);