diff options
Diffstat (limited to 'mm/memcontrol.c')
| -rw-r--r-- | mm/memcontrol.c | 354 |
1 files changed, 255 insertions, 99 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2bd3df3d101a..e6f0d5ef320a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1034,13 +1034,13 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) unsigned long limit; count = page_counter_read(&memcg->memory); - limit = READ_ONCE(memcg->memory.limit); + limit = READ_ONCE(memcg->memory.max); if (count < limit) margin = limit - count; if (do_memsw_account()) { count = page_counter_read(&memcg->memsw); - limit = READ_ONCE(memcg->memsw.limit); + limit = READ_ONCE(memcg->memsw.max); if (count <= limit) margin = min(margin, limit - count); else @@ -1148,13 +1148,13 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n", K((u64)page_counter_read(&memcg->memory)), - K((u64)memcg->memory.limit), memcg->memory.failcnt); + K((u64)memcg->memory.max), memcg->memory.failcnt); pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n", K((u64)page_counter_read(&memcg->memsw)), - K((u64)memcg->memsw.limit), memcg->memsw.failcnt); + K((u64)memcg->memsw.max), memcg->memsw.failcnt); pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n", K((u64)page_counter_read(&memcg->kmem)), - K((u64)memcg->kmem.limit), memcg->kmem.failcnt); + K((u64)memcg->kmem.max), memcg->kmem.failcnt); for_each_mem_cgroup_tree(iter, memcg) { pr_info("Memory cgroup stats for "); @@ -1179,21 +1179,21 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) /* * Return the memory (and swap, if configured) limit for a memcg. */ -unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg) +unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) { - unsigned long limit; + unsigned long max; - limit = memcg->memory.limit; + max = memcg->memory.max; if (mem_cgroup_swappiness(memcg)) { - unsigned long memsw_limit; - unsigned long swap_limit; + unsigned long memsw_max; + unsigned long swap_max; - memsw_limit = memcg->memsw.limit; - swap_limit = memcg->swap.limit; - swap_limit = min(swap_limit, (unsigned long)total_swap_pages); - limit = min(limit + swap_limit, memsw_limit); + memsw_max = memcg->memsw.max; + swap_max = memcg->swap.max; + swap_max = min(swap_max, (unsigned long)total_swap_pages); + max = min(max + swap_max, memsw_max); } - return limit; + return max; } static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, @@ -2444,12 +2444,13 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry, } #endif -static DEFINE_MUTEX(memcg_limit_mutex); +static DEFINE_MUTEX(memcg_max_mutex); -static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, - unsigned long limit, bool memsw) +static int mem_cgroup_resize_max(struct mem_cgroup *memcg, + unsigned long max, bool memsw) { bool enlarge = false; + bool drained = false; int ret; bool limits_invariant; struct page_counter *counter = memsw ? &memcg->memsw : &memcg->memory; @@ -2460,26 +2461,32 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, break; } - mutex_lock(&memcg_limit_mutex); + mutex_lock(&memcg_max_mutex); /* * Make sure that the new limit (memsw or memory limit) doesn't - * break our basic invariant rule memory.limit <= memsw.limit. + * break our basic invariant rule memory.max <= memsw.max. */ - limits_invariant = memsw ? limit >= memcg->memory.limit : - limit <= memcg->memsw.limit; + limits_invariant = memsw ? max >= memcg->memory.max : + max <= memcg->memsw.max; if (!limits_invariant) { - mutex_unlock(&memcg_limit_mutex); + mutex_unlock(&memcg_max_mutex); ret = -EINVAL; break; } - if (limit > counter->limit) + if (max > counter->max) enlarge = true; - ret = page_counter_limit(counter, limit); - mutex_unlock(&memcg_limit_mutex); + ret = page_counter_set_max(counter, max); + mutex_unlock(&memcg_max_mutex); if (!ret) break; + if (!drained) { + drain_all_stock(memcg); + drained = true; + continue; + } + if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, !memsw)) { ret = -EBUSY; @@ -2603,6 +2610,9 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) /* we call try-to-free pages for make this cgroup empty */ lru_add_drain_all(); + + drain_all_stock(memcg); + /* try to free all pages in this cgroup */ while (nr_retries && page_counter_read(&memcg->memory)) { int progress; @@ -2757,7 +2767,7 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, return (u64)mem_cgroup_usage(memcg, true) * PAGE_SIZE; return (u64)page_counter_read(counter) * PAGE_SIZE; case RES_LIMIT: - return (u64)counter->limit * PAGE_SIZE; + return (u64)counter->max * PAGE_SIZE; case RES_MAX_USAGE: return (u64)counter->watermark * PAGE_SIZE; case RES_FAILCNT: @@ -2871,24 +2881,24 @@ static void memcg_free_kmem(struct mem_cgroup *memcg) } #endif /* !CONFIG_SLOB */ -static int memcg_update_kmem_limit(struct mem_cgroup *memcg, - unsigned long limit) +static int memcg_update_kmem_max(struct mem_cgroup *memcg, + unsigned long max) { int ret; - mutex_lock(&memcg_limit_mutex); - ret = page_counter_limit(&memcg->kmem, limit); - mutex_unlock(&memcg_limit_mutex); + mutex_lock(&memcg_max_mutex); + ret = page_counter_set_max(&memcg->kmem, max); + mutex_unlock(&memcg_max_mutex); return ret; } -static int memcg_update_tcp_limit(struct mem_cgroup *memcg, unsigned long limit) +static int memcg_update_tcp_max(struct mem_cgroup *memcg, unsigned long max) { int ret; - mutex_lock(&memcg_limit_mutex); + mutex_lock(&memcg_max_mutex); - ret = page_counter_limit(&memcg->tcpmem, limit); + ret = page_counter_set_max(&memcg->tcpmem, max); if (ret) goto out; @@ -2913,7 +2923,7 @@ static int memcg_update_tcp_limit(struct mem_cgroup *memcg, unsigned long limit) memcg->tcpmem_active = true; } out: - mutex_unlock(&memcg_limit_mutex); + mutex_unlock(&memcg_max_mutex); return ret; } @@ -2941,16 +2951,16 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of, } switch (MEMFILE_TYPE(of_cft(of)->private)) { case _MEM: - ret = mem_cgroup_resize_limit(memcg, nr_pages, false); + ret = mem_cgroup_resize_max(memcg, nr_pages, false); break; case _MEMSWAP: - ret = mem_cgroup_resize_limit(memcg, nr_pages, true); + ret = mem_cgroup_resize_max(memcg, nr_pages, true); break; case _KMEM: - ret = memcg_update_kmem_limit(memcg, nr_pages); + ret = memcg_update_kmem_max(memcg, nr_pages); break; case _TCP: - ret = memcg_update_tcp_limit(memcg, nr_pages); + ret = memcg_update_tcp_max(memcg, nr_pages); break; } break; @@ -3083,7 +3093,7 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v) #endif /* CONFIG_NUMA */ /* Universal VM events cgroup1 shows, original sort order */ -unsigned int memcg1_events[] = { +static const unsigned int memcg1_events[] = { PGPGIN, PGPGOUT, PGFAULT, @@ -3126,8 +3136,8 @@ static int memcg_stat_show(struct seq_file *m, void *v) /* Hierarchical information */ memory = memsw = PAGE_COUNTER_MAX; for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) { - memory = min(memory, mi->memory.limit); - memsw = min(memsw, mi->memsw.limit); + memory = min(memory, mi->memory.max); + memsw = min(memsw, mi->memsw.max); } seq_printf(m, "hierarchical_memory_limit %llu\n", (u64)memory * PAGE_SIZE); @@ -3540,7 +3550,8 @@ static int mem_cgroup_oom_control_read(struct seq_file *sf, void *v) seq_printf(sf, "oom_kill_disable %d\n", memcg->oom_kill_disable); seq_printf(sf, "under_oom %d\n", (bool)memcg->under_oom); - seq_printf(sf, "oom_kill %lu\n", memcg_sum_events(memcg, OOM_KILL)); + seq_printf(sf, "oom_kill %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL])); return 0; } @@ -3562,11 +3573,6 @@ static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css, #ifdef CONFIG_CGROUP_WRITEBACK -struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg) -{ - return &memcg->cgwb_list; -} - static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp) { return wb_domain_init(&memcg->cgwb_domain, gfp); @@ -3626,7 +3632,7 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, *pheadroom = PAGE_COUNTER_MAX; while ((parent = parent_mem_cgroup(memcg))) { - unsigned long ceiling = min(memcg->memory.limit, memcg->high); + unsigned long ceiling = min(memcg->memory.max, memcg->high); unsigned long used = page_counter_read(&memcg->memory); *pheadroom = min(*pheadroom, ceiling - min(ceiling, used)); @@ -3849,7 +3855,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, if (ret) goto out_put_css; - efile.file->f_op->poll(efile.file, &event->pt); + vfs_poll(efile.file, &event->pt); spin_lock(&memcg->event_list_lock); list_add(&event->list, &memcg->event_list); @@ -4270,7 +4276,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) } spin_unlock(&memcg->event_list_lock); - memcg->low = 0; + page_counter_set_min(&memcg->memory, 0); + page_counter_set_low(&memcg->memory, 0); memcg_offline_kmem(memcg); wb_memcg_offline(memcg); @@ -4319,12 +4326,13 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - page_counter_limit(&memcg->memory, PAGE_COUNTER_MAX); - page_counter_limit(&memcg->swap, PAGE_COUNTER_MAX); - page_counter_limit(&memcg->memsw, PAGE_COUNTER_MAX); - page_counter_limit(&memcg->kmem, PAGE_COUNTER_MAX); - page_counter_limit(&memcg->tcpmem, PAGE_COUNTER_MAX); - memcg->low = 0; + page_counter_set_max(&memcg->memory, PAGE_COUNTER_MAX); + page_counter_set_max(&memcg->swap, PAGE_COUNTER_MAX); + page_counter_set_max(&memcg->memsw, PAGE_COUNTER_MAX); + page_counter_set_max(&memcg->kmem, PAGE_COUNTER_MAX); + page_counter_set_max(&memcg->tcpmem, PAGE_COUNTER_MAX); + page_counter_set_min(&memcg->memory, 0); + page_counter_set_low(&memcg->memory, 0); memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; memcg_wb_domain_size_changed(memcg); @@ -5061,10 +5069,40 @@ static u64 memory_current_read(struct cgroup_subsys_state *css, return (u64)page_counter_read(&memcg->memory) * PAGE_SIZE; } +static int memory_min_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + unsigned long min = READ_ONCE(memcg->memory.min); + + if (min == PAGE_COUNTER_MAX) + seq_puts(m, "max\n"); + else + seq_printf(m, "%llu\n", (u64)min * PAGE_SIZE); + + return 0; +} + +static ssize_t memory_min_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long min; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "max", &min); + if (err) + return err; + + page_counter_set_min(&memcg->memory, min); + + return nbytes; +} + static int memory_low_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - unsigned long low = READ_ONCE(memcg->low); + unsigned long low = READ_ONCE(memcg->memory.low); if (low == PAGE_COUNTER_MAX) seq_puts(m, "max\n"); @@ -5086,7 +5124,7 @@ static ssize_t memory_low_write(struct kernfs_open_file *of, if (err) return err; - memcg->low = low; + page_counter_set_low(&memcg->memory, low); return nbytes; } @@ -5131,7 +5169,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, static int memory_max_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - unsigned long max = READ_ONCE(memcg->memory.limit); + unsigned long max = READ_ONCE(memcg->memory.max); if (max == PAGE_COUNTER_MAX) seq_puts(m, "max\n"); @@ -5155,7 +5193,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, if (err) return err; - xchg(&memcg->memory.limit, max); + xchg(&memcg->memory.max, max); for (;;) { unsigned long nr_pages = page_counter_read(&memcg->memory); @@ -5202,7 +5240,8 @@ static int memory_events_show(struct seq_file *m, void *v) atomic_long_read(&memcg->memory_events[MEMCG_MAX])); seq_printf(m, "oom %lu\n", atomic_long_read(&memcg->memory_events[MEMCG_OOM])); - seq_printf(m, "oom_kill %lu\n", memcg_sum_events(memcg, OOM_KILL)); + seq_printf(m, "oom_kill %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL])); return 0; } @@ -5296,6 +5335,12 @@ static struct cftype memory_files[] = { .read_u64 = memory_current_read, }, { + .name = "min", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_min_show, + .write = memory_min_write, + }, + { .name = "low", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = memory_low_show, @@ -5344,54 +5389,144 @@ struct cgroup_subsys memory_cgrp_subsys = { }; /** - * mem_cgroup_low - check if memory consumption is below the normal range + * mem_cgroup_protected - check if memory consumption is in the normal range * @root: the top ancestor of the sub-tree being checked * @memcg: the memory cgroup to check * - * Returns %true if memory consumption of @memcg, and that of all - * ancestors up to (but not including) @root, is below the normal range. + * WARNING: This function is not stateless! It can only be used as part + * of a top-down tree iteration, not for isolated queries. + * + * Returns one of the following: + * MEMCG_PROT_NONE: cgroup memory is not protected + * MEMCG_PROT_LOW: cgroup memory is protected as long there is + * an unprotected supply of reclaimable memory from other cgroups. + * MEMCG_PROT_MIN: cgroup memory is protected + * + * @root is exclusive; it is never protected when looked at directly * - * @root is exclusive; it is never low when looked at directly and isn't - * checked when traversing the hierarchy. + * To provide a proper hierarchical behavior, effective memory.min/low values + * are used. Below is the description of how effective memory.low is calculated. + * Effective memory.min values is calculated in the same way. * - * Excluding @root enables using memory.low to prioritize memory usage - * between cgroups within a subtree of the hierarchy that is limited by - * memory.high or memory.max. + * Effective memory.low is always equal or less than the original memory.low. + * If there is no memory.low overcommittment (which is always true for + * top-level memory cgroups), these two values are equal. + * Otherwise, it's a part of parent's effective memory.low, + * calculated as a cgroup's memory.low usage divided by sum of sibling's + * memory.low usages, where memory.low usage is the size of actually + * protected memory. * - * For example, given cgroup A with children B and C: + * low_usage + * elow = min( memory.low, parent->elow * ------------------ ), + * siblings_low_usage * - * A - * / \ - * B C + * | memory.current, if memory.current < memory.low + * low_usage = | + | 0, otherwise. * - * and * - * 1. A/memory.current > A/memory.high - * 2. A/B/memory.current < A/B/memory.low - * 3. A/C/memory.current >= A/C/memory.low + * Such definition of the effective memory.low provides the expected + * hierarchical behavior: parent's memory.low value is limiting + * children, unprotected memory is reclaimed first and cgroups, + * which are not using their guarantee do not affect actual memory + * distribution. * - * As 'A' is high, i.e. triggers reclaim from 'A', and 'B' is low, we - * should reclaim from 'C' until 'A' is no longer high or until we can - * no longer reclaim from 'C'. If 'A', i.e. @root, isn't excluded by - * mem_cgroup_low when reclaming from 'A', then 'B' won't be considered - * low and we will reclaim indiscriminately from both 'B' and 'C'. + * For example, if there are memcgs A, A/B, A/C, A/D and A/E: + * + * A A/memory.low = 2G, A/memory.current = 6G + * //\\ + * BC DE B/memory.low = 3G B/memory.current = 2G + * C/memory.low = 1G C/memory.current = 2G + * D/memory.low = 0 D/memory.current = 2G + * E/memory.low = 10G E/memory.current = 0 + * + * and the memory pressure is applied, the following memory distribution + * is expected (approximately): + * + * A/memory.current = 2G + * + * B/memory.current = 1.3G + * C/memory.current = 0.6G + * D/memory.current = 0 + * E/memory.current = 0 + * + * These calculations require constant tracking of the actual low usages + * (see propagate_protected_usage()), as well as recursive calculation of + * effective memory.low values. But as we do call mem_cgroup_protected() + * path for each memory cgroup top-down from the reclaim, + * it's possible to optimize this part, and save calculated elow + * for next usage. This part is intentionally racy, but it's ok, + * as memory.low is a best-effort mechanism. */ -bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg) +enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, + struct mem_cgroup *memcg) { + struct mem_cgroup *parent; + unsigned long emin, parent_emin; + unsigned long elow, parent_elow; + unsigned long usage; + if (mem_cgroup_disabled()) - return false; + return MEMCG_PROT_NONE; if (!root) root = root_mem_cgroup; if (memcg == root) - return false; + return MEMCG_PROT_NONE; + + usage = page_counter_read(&memcg->memory); + if (!usage) + return MEMCG_PROT_NONE; - for (; memcg != root; memcg = parent_mem_cgroup(memcg)) { - if (page_counter_read(&memcg->memory) >= memcg->low) - return false; + emin = memcg->memory.min; + elow = memcg->memory.low; + + parent = parent_mem_cgroup(memcg); + /* No parent means a non-hierarchical mode on v1 memcg */ + if (!parent) + return MEMCG_PROT_NONE; + + if (parent == root) + goto exit; + + parent_emin = READ_ONCE(parent->memory.emin); + emin = min(emin, parent_emin); + if (emin && parent_emin) { + unsigned long min_usage, siblings_min_usage; + + min_usage = min(usage, memcg->memory.min); + siblings_min_usage = atomic_long_read( + &parent->memory.children_min_usage); + + if (min_usage && siblings_min_usage) + emin = min(emin, parent_emin * min_usage / + siblings_min_usage); } - return true; + parent_elow = READ_ONCE(parent->memory.elow); + elow = min(elow, parent_elow); + if (elow && parent_elow) { + unsigned long low_usage, siblings_low_usage; + + low_usage = min(usage, memcg->memory.low); + siblings_low_usage = atomic_long_read( + &parent->memory.children_low_usage); + + if (low_usage && siblings_low_usage) + elow = min(elow, parent_elow * low_usage / + siblings_low_usage); + } + +exit: + memcg->memory.emin = emin; + memcg->memory.elow = elow; + + if (usage <= emin) + return MEMCG_PROT_MIN; + else if (usage <= elow) + return MEMCG_PROT_LOW; + else + return MEMCG_PROT_NONE; } /** @@ -6012,10 +6147,17 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) if (!memcg) return 0; + if (!entry.val) { + memcg_memory_event(memcg, MEMCG_SWAP_FAIL); + return 0; + } + memcg = mem_cgroup_id_get_online(memcg); if (!mem_cgroup_is_root(memcg) && !page_counter_try_charge(&memcg->swap, nr_pages, &counter)) { + memcg_memory_event(memcg, MEMCG_SWAP_MAX); + memcg_memory_event(memcg, MEMCG_SWAP_FAIL); mem_cgroup_id_put(memcg); return -ENOMEM; } @@ -6067,7 +6209,7 @@ long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) return nr_swap_pages; for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) nr_swap_pages = min_t(long, nr_swap_pages, - READ_ONCE(memcg->swap.limit) - + READ_ONCE(memcg->swap.max) - page_counter_read(&memcg->swap)); return nr_swap_pages; } @@ -6088,7 +6230,7 @@ bool mem_cgroup_swap_full(struct page *page) return false; for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) - if (page_counter_read(&memcg->swap) * 2 >= memcg->swap.limit) + if (page_counter_read(&memcg->swap) * 2 >= memcg->swap.max) return true; return false; @@ -6122,7 +6264,7 @@ static u64 swap_current_read(struct cgroup_subsys_state *css, static int swap_max_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - unsigned long max = READ_ONCE(memcg->swap.limit); + unsigned long max = READ_ONCE(memcg->swap.max); if (max == PAGE_COUNTER_MAX) seq_puts(m, "max\n"); @@ -6144,15 +6286,23 @@ static ssize_t swap_max_write(struct kernfs_open_file *of, if (err) return err; - mutex_lock(&memcg_limit_mutex); - err = page_counter_limit(&memcg->swap, max); - mutex_unlock(&memcg_limit_mutex); - if (err) - return err; + xchg(&memcg->swap.max, max); return nbytes; } +static int swap_events_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + + seq_printf(m, "max %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_SWAP_MAX])); + seq_printf(m, "fail %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_SWAP_FAIL])); + + return 0; +} + static struct cftype swap_files[] = { { .name = "swap.current", @@ -6165,6 +6315,12 @@ static struct cftype swap_files[] = { .seq_show = swap_max_show, .write = swap_max_write, }, + { + .name = "swap.events", + .flags = CFTYPE_NOT_ON_ROOT, + .file_offset = offsetof(struct mem_cgroup, swap_events_file), + .seq_show = swap_events_show, + }, { } /* terminate */ }; |