#include <linux/limits.h>
#include <linux/mutex.h>
#include <linux/rbtree.h>
-#include <linux/shmem_fs.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/swapops.h>
static void mem_cgroup_threshold(struct mem_cgroup *mem);
static void mem_cgroup_oom_notify(struct mem_cgroup *mem);
+enum {
+ SCAN_BY_LIMIT,
+ SCAN_BY_SYSTEM,
+ NR_SCAN_CONTEXT,
+ SCAN_BY_SHRINK, /* not recorded now */
+};
+
+enum {
+ SCAN,
+ SCAN_ANON,
+ SCAN_FILE,
+ ROTATE,
+ ROTATE_ANON,
+ ROTATE_FILE,
+ FREED,
+ FREED_ANON,
+ FREED_FILE,
+ ELAPSED,
+ NR_SCANSTATS,
+};
+
+struct scanstat {
+ spinlock_t lock;
+ unsigned long stats[NR_SCAN_CONTEXT][NR_SCANSTATS];
+ unsigned long rootstats[NR_SCAN_CONTEXT][NR_SCANSTATS];
+};
+
+const char *scanstat_string[NR_SCANSTATS] = {
+ "scanned_pages",
+ "scanned_anon_pages",
+ "scanned_file_pages",
+ "rotated_pages",
+ "rotated_anon_pages",
+ "rotated_file_pages",
+ "freed_pages",
+ "freed_anon_pages",
+ "freed_file_pages",
+ "elapsed_ns",
+};
+#define SCANSTAT_WORD_LIMIT "_by_limit"
+#define SCANSTAT_WORD_SYSTEM "_by_system"
+#define SCANSTAT_WORD_HIERARCHY "_under_hierarchy"
+
+
/*
* The memory controller data structure. The memory controller controls both
* page cache and RSS per cgroup. We would eventually like to provide
/* For oom notifier event fd */
struct list_head oom_notify;
-
+ /* For recording LRU-scan statistics */
+ struct scanstat scanstat;
/*
* Should we move charges of a task when a task is moved into this
* mem_cgroup ? And what type of charges should we move ?
mem_cgroup_add_lru_list(page, to);
}
+/*
+ * Checks whether given mem is same or in the root_mem's
+ * hierarchy subtree
+ */
+static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_mem,
+ struct mem_cgroup *mem)
+{
+ if (root_mem != mem) {
+ return (root_mem->use_hierarchy &&
+ css_is_ancestor(&mem->css, &root_mem->css));
+ }
+
+ return true;
+}
+
int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
{
int ret;
* enabled in "curr" and "curr" is a child of "mem" in *cgroup*
* hierarchy(even if use_hierarchy is disabled in "mem").
*/
- if (mem->use_hierarchy)
- ret = css_is_ancestor(&curr->css, &mem->css);
- else
- ret = (curr == mem);
+ ret = mem_cgroup_same_or_subtree(mem, curr);
css_put(&curr->css);
return ret;
}
to = mc.to;
if (!from)
goto unlock;
- if (from == mem || to == mem
- || (mem->use_hierarchy && css_is_ancestor(&from->css, &mem->css))
- || (mem->use_hierarchy && css_is_ancestor(&to->css, &mem->css)))
- ret = true;
+
+ ret = mem_cgroup_same_or_subtree(mem, from)
+ || mem_cgroup_same_or_subtree(mem, to);
unlock:
spin_unlock(&mc.lock);
return ret;
}
#endif
+static void __mem_cgroup_record_scanstat(unsigned long *stats,
+ struct memcg_scanrecord *rec)
+{
+
+ stats[SCAN] += rec->nr_scanned[0] + rec->nr_scanned[1];
+ stats[SCAN_ANON] += rec->nr_scanned[0];
+ stats[SCAN_FILE] += rec->nr_scanned[1];
+
+ stats[ROTATE] += rec->nr_rotated[0] + rec->nr_rotated[1];
+ stats[ROTATE_ANON] += rec->nr_rotated[0];
+ stats[ROTATE_FILE] += rec->nr_rotated[1];
+
+ stats[FREED] += rec->nr_freed[0] + rec->nr_freed[1];
+ stats[FREED_ANON] += rec->nr_freed[0];
+ stats[FREED_FILE] += rec->nr_freed[1];
+
+ stats[ELAPSED] += rec->elapsed;
+}
+
+static void mem_cgroup_record_scanstat(struct memcg_scanrecord *rec)
+{
+ struct mem_cgroup *mem;
+ int context = rec->context;
+
+ if (context >= NR_SCAN_CONTEXT)
+ return;
+
+ mem = rec->mem;
+ spin_lock(&mem->scanstat.lock);
+ __mem_cgroup_record_scanstat(mem->scanstat.stats[context], rec);
+ spin_unlock(&mem->scanstat.lock);
+
+ mem = rec->root;
+ spin_lock(&mem->scanstat.lock);
+ __mem_cgroup_record_scanstat(mem->scanstat.rootstats[context], rec);
+ spin_unlock(&mem->scanstat.lock);
+}
+
/*
* Scan the hierarchy if needed to reclaim memory. We remember the last child
* we reclaimed from, so that we don't end up penalizing one child extensively
bool noswap = reclaim_options & MEM_CGROUP_RECLAIM_NOSWAP;
bool shrink = reclaim_options & MEM_CGROUP_RECLAIM_SHRINK;
bool check_soft = reclaim_options & MEM_CGROUP_RECLAIM_SOFT;
+ struct memcg_scanrecord rec;
unsigned long excess;
- unsigned long nr_scanned;
+ unsigned long scanned;
excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT;
/* If memsw_is_minimum==1, swap-out is of-no-use. */
- if (!check_soft && root_mem->memsw_is_minimum)
+ if (!check_soft && !shrink && root_mem->memsw_is_minimum)
noswap = true;
+ if (shrink)
+ rec.context = SCAN_BY_SHRINK;
+ else if (check_soft)
+ rec.context = SCAN_BY_SYSTEM;
+ else
+ rec.context = SCAN_BY_LIMIT;
+
+ rec.root = root_mem;
+
while (1) {
victim = mem_cgroup_select_victim(root_mem);
if (victim == root_mem) {
css_put(&victim->css);
continue;
}
+ rec.mem = victim;
+ rec.nr_scanned[0] = 0;
+ rec.nr_scanned[1] = 0;
+ rec.nr_rotated[0] = 0;
+ rec.nr_rotated[1] = 0;
+ rec.nr_freed[0] = 0;
+ rec.nr_freed[1] = 0;
+ rec.elapsed = 0;
/* we use swappiness of local cgroup */
if (check_soft) {
ret = mem_cgroup_shrink_node_zone(victim, gfp_mask,
- noswap, zone, &nr_scanned);
- *total_scanned += nr_scanned;
+ noswap, zone, &rec, &scanned);
+ *total_scanned += scanned;
} else
ret = try_to_free_mem_cgroup_pages(victim, gfp_mask,
- noswap);
+ noswap, &rec);
+ mem_cgroup_record_scanstat(&rec);
css_put(&victim->css);
/*
* At shrinking usage, we can't check we should stop here or
/*
* Check OOM-Killer is already running under our hierarchy.
* If someone is running, return false.
- * Has to be called with memcg_oom_mutex
+ * Has to be called with memcg_oom_lock
*/
static bool mem_cgroup_oom_lock(struct mem_cgroup *mem)
{
}
/*
- * Has to be called with memcg_oom_mutex
+ * Has to be called with memcg_oom_lock
*/
static int mem_cgroup_oom_unlock(struct mem_cgroup *mem)
{
atomic_add_unless(&iter->under_oom, -1, 0);
}
-static DEFINE_MUTEX(memcg_oom_mutex);
+static DEFINE_SPINLOCK(memcg_oom_lock);
static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);
struct oom_wait_info {
static int memcg_oom_wake_function(wait_queue_t *wait,
unsigned mode, int sync, void *arg)
{
- struct mem_cgroup *wake_mem = (struct mem_cgroup *)arg;
+ struct mem_cgroup *wake_mem = (struct mem_cgroup *)arg,
+ *oom_wait_mem;
struct oom_wait_info *oom_wait_info;
oom_wait_info = container_of(wait, struct oom_wait_info, wait);
+ oom_wait_mem = oom_wait_info->mem;
- if (oom_wait_info->mem == wake_mem)
- goto wakeup;
- /* if no hierarchy, no match */
- if (!oom_wait_info->mem->use_hierarchy || !wake_mem->use_hierarchy)
- return 0;
/*
* Both of oom_wait_info->mem and wake_mem are stable under us.
* Then we can use css_is_ancestor without taking care of RCU.
*/
- if (!css_is_ancestor(&oom_wait_info->mem->css, &wake_mem->css) &&
- !css_is_ancestor(&wake_mem->css, &oom_wait_info->mem->css))
+ if (!mem_cgroup_same_or_subtree(oom_wait_mem, wake_mem)
+ && !mem_cgroup_same_or_subtree(wake_mem, oom_wait_mem))
return 0;
-
-wakeup:
return autoremove_wake_function(wait, mode, sync, arg);
}
mem_cgroup_mark_under_oom(mem);
/* At first, try to OOM lock hierarchy under mem.*/
- mutex_lock(&memcg_oom_mutex);
+ spin_lock(&memcg_oom_lock);
locked = mem_cgroup_oom_lock(mem);
/*
* Even if signal_pending(), we can't quit charge() loop without
need_to_kill = false;
if (locked)
mem_cgroup_oom_notify(mem);
- mutex_unlock(&memcg_oom_mutex);
+ spin_unlock(&memcg_oom_lock);
if (need_to_kill) {
finish_wait(&memcg_oom_waitq, &owait.wait);
schedule();
finish_wait(&memcg_oom_waitq, &owait.wait);
}
- mutex_lock(&memcg_oom_mutex);
+ spin_lock(&memcg_oom_lock);
if (locked)
mem_cgroup_oom_unlock(mem);
memcg_wakeup_oom(mem);
- mutex_unlock(&memcg_oom_mutex);
+ spin_unlock(&memcg_oom_lock);
mem_cgroup_unmark_under_oom(mem);
}
/*
- * Tries to drain stocked charges in other cpus. This function is asynchronous
- * and just put a work per cpu for draining localy on each cpu. Caller can
- * expects some charges will be back to res_counter later but cannot wait for
- * it.
+ * Drains all per-CPU charge caches for given root_mem resp. subtree
+ * of the hierarchy under it. sync flag says whether we should block
+ * until the work is done.
*/
-static void drain_all_stock_async(struct mem_cgroup *root_mem)
+static void drain_all_stock(struct mem_cgroup *root_mem, bool sync)
{
int cpu, curcpu;
- /*
- * If someone calls draining, avoid adding more kworker runs.
- */
- if (!mutex_trylock(&percpu_charge_mutex))
- return;
+
/* Notify other cpus that system-wide "drain" is running */
get_online_cpus();
/*
struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
struct mem_cgroup *mem;
- if (cpu == curcpu)
- continue;
-
mem = stock->cached;
- if (!mem)
+ if (!mem || !stock->nr_pages)
+ continue;
+ if (!mem_cgroup_same_or_subtree(root_mem, mem))
continue;
- if (mem != root_mem) {
- if (!root_mem->use_hierarchy)
- continue;
- /* check whether "mem" is under tree of "root_mem" */
- if (!css_is_ancestor(&mem->css, &root_mem->css))
- continue;
+ if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) {
+ if (cpu == curcpu)
+ drain_local_stock(&stock->work);
+ else
+ schedule_work_on(cpu, &stock->work);
}
- if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags))
- schedule_work_on(cpu, &stock->work);
}
+
+ if (!sync)
+ goto out;
+
+ for_each_online_cpu(cpu) {
+ struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
+ if (test_bit(FLUSHING_CACHED_CHARGE, &stock->flags))
+ flush_work(&stock->work);
+ }
+out:
put_online_cpus();
+}
+
+/*
+ * Tries to drain stocked charges in other cpus. This function is asynchronous
+ * and just put a work per cpu for draining localy on each cpu. Caller can
+ * expects some charges will be back to res_counter later but cannot wait for
+ * it.
+ */
+static void drain_all_stock_async(struct mem_cgroup *root_mem)
+{
+ /*
+ * If someone calls draining, avoid adding more kworker runs.
+ */
+ if (!mutex_trylock(&percpu_charge_mutex))
+ return;
+ drain_all_stock(root_mem, false);
mutex_unlock(&percpu_charge_mutex);
- /* We don't wait for flush_work */
}
/* This is a synchronous drain interface. */
-static void drain_all_stock_sync(void)
+static void drain_all_stock_sync(struct mem_cgroup *root_mem)
{
/* called when force_empty is called */
mutex_lock(&percpu_charge_mutex);
- schedule_on_each_cpu(drain_local_stock);
+ drain_all_stock(root_mem, true);
mutex_unlock(&percpu_charge_mutex);
}
return 0;
if (PageCompound(page))
return 0;
- /*
- * Corner case handling. This is called from add_to_page_cache()
- * in usual. But some FS (shmem) precharges this page before calling it
- * and call add_to_page_cache() with GFP_NOWAIT.
- *
- * For GFP_NOWAIT case, the page may be pre-charged before calling
- * add_to_page_cache(). (See shmem.c) check it here and avoid to call
- * charge twice. (It works but has to pay a bit larger cost.)
- * And when the page is SwapCache, it should take swap information
- * into account. This is under lock_page() now.
- */
- if (!(gfp_mask & __GFP_WAIT)) {
- struct page_cgroup *pc;
-
- pc = lookup_page_cgroup(page);
- if (!pc)
- return 0;
- lock_page_cgroup(pc);
- if (PageCgroupUsed(pc)) {
- unlock_page_cgroup(pc);
- return 0;
- }
- unlock_page_cgroup(pc);
- }
if (unlikely(!mm))
mm = &init_mm;
cgroup_release_and_wakeup_rmdir(&mem->css);
}
-/*
- * A call to try to shrink memory usage on charge failure at shmem's swapin.
- * Calling hierarchical_reclaim is not enough because we should update
- * last_oom_jiffies to prevent pagefault_out_of_memory from invoking global OOM.
- * Moreover considering hierarchy, we should reclaim from the mem_over_limit,
- * not from the memcg which this page would be charged to.
- * try_charge_swapin does all of these works properly.
- */
-int mem_cgroup_shmem_charge_fallback(struct page *page,
- struct mm_struct *mm,
- gfp_t gfp_mask)
-{
- struct mem_cgroup *mem;
- int ret;
-
- if (mem_cgroup_disabled())
- return 0;
-
- ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem);
- if (!ret)
- mem_cgroup_cancel_charge_swapin(mem); /* it does !mem check */
-
- return ret;
-}
-
#ifdef CONFIG_DEBUG_VM
static struct page_cgroup *lookup_page_cgroup_used(struct page *page)
{
goto out;
/* This is for making all *used* pages to be on LRU. */
lru_add_drain_all();
- drain_all_stock_sync();
+ drain_all_stock_sync(mem);
ret = 0;
mem_cgroup_start_move(mem);
for_each_node_state(node, N_HIGH_MEMORY) {
/* try to free all pages in this cgroup */
shrink = 1;
while (nr_retries && mem->res.usage > 0) {
+ struct memcg_scanrecord rec;
int progress;
if (signal_pending(current)) {
ret = -EINTR;
goto out;
}
+ rec.context = SCAN_BY_SHRINK;
+ rec.mem = mem;
+ rec.root = mem;
progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL,
- false);
+ false, &rec);
if (!progress) {
nr_retries--;
/* maybe some writeback is necessary */
if (!event)
return -ENOMEM;
- mutex_lock(&memcg_oom_mutex);
+ spin_lock(&memcg_oom_lock);
event->eventfd = eventfd;
list_add(&event->list, &memcg->oom_notify);
/* already in OOM ? */
if (atomic_read(&memcg->under_oom))
eventfd_signal(eventfd, 1);
- mutex_unlock(&memcg_oom_mutex);
+ spin_unlock(&memcg_oom_lock);
return 0;
}
BUG_ON(type != _OOM_TYPE);
- mutex_lock(&memcg_oom_mutex);
+ spin_lock(&memcg_oom_lock);
list_for_each_entry_safe(ev, tmp, &mem->oom_notify, list) {
if (ev->eventfd == eventfd) {
}
}
- mutex_unlock(&memcg_oom_mutex);
+ spin_unlock(&memcg_oom_lock);
}
static int mem_cgroup_oom_control_read(struct cgroup *cgrp,
}
#endif /* CONFIG_NUMA */
+static int mem_cgroup_vmscan_stat_read(struct cgroup *cgrp,
+ struct cftype *cft,
+ struct cgroup_map_cb *cb)
+{
+ struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
+ char string[64];
+ int i;
+
+ for (i = 0; i < NR_SCANSTATS; i++) {
+ strcpy(string, scanstat_string[i]);
+ strcat(string, SCANSTAT_WORD_LIMIT);
+ cb->fill(cb, string, mem->scanstat.stats[SCAN_BY_LIMIT][i]);
+ }
+
+ for (i = 0; i < NR_SCANSTATS; i++) {
+ strcpy(string, scanstat_string[i]);
+ strcat(string, SCANSTAT_WORD_SYSTEM);
+ cb->fill(cb, string, mem->scanstat.stats[SCAN_BY_SYSTEM][i]);
+ }
+
+ for (i = 0; i < NR_SCANSTATS; i++) {
+ strcpy(string, scanstat_string[i]);
+ strcat(string, SCANSTAT_WORD_LIMIT);
+ strcat(string, SCANSTAT_WORD_HIERARCHY);
+ cb->fill(cb, string, mem->scanstat.rootstats[SCAN_BY_LIMIT][i]);
+ }
+ for (i = 0; i < NR_SCANSTATS; i++) {
+ strcpy(string, scanstat_string[i]);
+ strcat(string, SCANSTAT_WORD_SYSTEM);
+ strcat(string, SCANSTAT_WORD_HIERARCHY);
+ cb->fill(cb, string, mem->scanstat.rootstats[SCAN_BY_SYSTEM][i]);
+ }
+ return 0;
+}
+
+static int mem_cgroup_reset_vmscan_stat(struct cgroup *cgrp,
+ unsigned int event)
+{
+ struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
+
+ spin_lock(&mem->scanstat.lock);
+ memset(&mem->scanstat.stats, 0, sizeof(mem->scanstat.stats));
+ memset(&mem->scanstat.rootstats, 0, sizeof(mem->scanstat.rootstats));
+ spin_unlock(&mem->scanstat.lock);
+ return 0;
+}
+
+
static struct cftype mem_cgroup_files[] = {
{
.name = "usage_in_bytes",
.mode = S_IRUGO,
},
#endif
+ {
+ .name = "vmscan_stat",
+ .read_map = mem_cgroup_vmscan_stat_read,
+ .trigger = mem_cgroup_reset_vmscan_stat,
+ },
};
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
atomic_set(&mem->refcnt, 1);
mem->move_charge_at_immigrate = 0;
mutex_init(&mem->thresholds_lock);
+ spin_lock_init(&mem->scanstat.lock);
return &mem->css;
free_out:
__mem_cgroup_free(mem);
pgoff = pte_to_pgoff(ptent);
/* page is moved even if it's not RSS of this task(page-faulted). */
- if (!mapping_cap_swap_backed(mapping)) { /* normal file */
- page = find_get_page(mapping, pgoff);
- } else { /* shmem/tmpfs file. we should take account of swap too. */
- swp_entry_t ent;
- mem_cgroup_get_shmem_target(inode, pgoff, &page, &ent);
+ page = find_get_page(mapping, pgoff);
+
+#ifdef CONFIG_SWAP
+ /* shmem/tmpfs may report page out on swap: account for that too. */
+ if (radix_tree_exceptional_entry(page)) {
+ swp_entry_t swap = radix_to_swp_entry(page);
if (do_swap_account)
- entry->val = ent.val;
+ *entry = swap;
+ page = find_get_page(&swapper_space, swap.val);
}
-
+#endif
return page;
}
projects / ~andy / linux / blobdiff