/* vmpressure notifications */
struct vmpressure vmpressure;
- union {
- /*
- * the counter to account for mem+swap usage.
- */
- struct res_counter memsw;
-
- /*
- * rcu_freeing is used only when freeing struct mem_cgroup,
- * so put it into a union to avoid wasting more memory.
- * It must be disjoint from the css field. It could be
- * in a union with the res field, but res plays a much
- * larger part in mem_cgroup life than memsw, and might
- * be of interest, even at time of free, when debugging.
- * So share rcu_head with the less interesting memsw.
- */
- struct rcu_head rcu_freeing;
- /*
- * We also need some space for a worker in deferred freeing.
- * By the time we call it, rcu_freeing is no longer in use.
- */
- struct work_struct work_freeing;
- };
+ /*
+ * the counter to account for mem+swap usage.
+ */
+ struct res_counter memsw;
/*
* the counter to account for kernel memory usage.
bool oom_lock;
atomic_t under_oom;
- atomic_t refcnt;
-
int swappiness;
/* OOM-Killer disable */
int oom_kill_disable;
*/
static DEFINE_MUTEX(memcg_create_mutex);
-static void mem_cgroup_get(struct mem_cgroup *memcg);
-static void mem_cgroup_put(struct mem_cgroup *memcg);
-
static inline
struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s)
{
unlock_page_cgroup(pc);
/*
* even after unlock, we have memcg->res.usage here and this memcg
- * will never be freed.
+ * 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);
- mem_cgroup_get(memcg);
+ css_get(&memcg->css);
}
/*
* Migration does not charge the res_counter for the
/*
* record memcg information, if swapout && memcg != NULL,
- * mem_cgroup_get() was called in uncharge().
+ * css_get() was called in uncharge().
*/
if (do_swap_account && swapout && memcg)
swap_cgroup_record(ent, css_id(&memcg->css));
if (!mem_cgroup_is_root(memcg))
res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
mem_cgroup_swap_statistics(memcg, false);
- mem_cgroup_put(memcg);
+ css_put(&memcg->css);
}
rcu_read_unlock();
}
* This function is only called from task migration context now.
* It postpones res_counter and refcount handling till the end
* of task migration(mem_cgroup_clear_mc()) for performance
- * improvement. But we cannot postpone mem_cgroup_get(to)
- * because if the process that has been moved to @to does
- * swap-in, the refcount of @to might be decreased to 0.
+ * improvement. But we cannot postpone css_get(to) because if
+ * the process that has been moved to @to does swap-in, the
+ * refcount of @to might be decreased to 0.
+ *
+ * We are in attach() phase, so the cgroup is guaranteed to be
+ * alive, so we can just call css_get().
*/
- mem_cgroup_get(to);
+ css_get(&to->css);
return 0;
}
return -EINVAL;
vfree(memcg);
}
-
-/*
- * Helpers for freeing a kmalloc()ed/vzalloc()ed mem_cgroup by RCU,
- * but in process context. The work_freeing structure is overlaid
- * on the rcu_freeing structure, which itself is overlaid on memsw.
- */
-static void free_work(struct work_struct *work)
-{
- struct mem_cgroup *memcg;
-
- memcg = container_of(work, struct mem_cgroup, work_freeing);
- __mem_cgroup_free(memcg);
-}
-
-static void free_rcu(struct rcu_head *rcu_head)
-{
- struct mem_cgroup *memcg;
-
- memcg = container_of(rcu_head, struct mem_cgroup, rcu_freeing);
- INIT_WORK(&memcg->work_freeing, free_work);
- schedule_work(&memcg->work_freeing);
-}
-
-static void mem_cgroup_get(struct mem_cgroup *memcg)
-{
- atomic_inc(&memcg->refcnt);
-}
-
-static void __mem_cgroup_put(struct mem_cgroup *memcg, int count)
-{
- if (atomic_sub_and_test(count, &memcg->refcnt)) {
- struct mem_cgroup *parent = parent_mem_cgroup(memcg);
- call_rcu(&memcg->rcu_freeing, free_rcu);
- if (parent)
- mem_cgroup_put(parent);
- }
-}
-
-static void mem_cgroup_put(struct mem_cgroup *memcg)
-{
- __mem_cgroup_put(memcg, 1);
-}
-
/*
* Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled.
*/
memcg->last_scanned_node = MAX_NUMNODES;
INIT_LIST_HEAD(&memcg->oom_notify);
- atomic_set(&memcg->refcnt, 1);
memcg->move_charge_at_immigrate = 0;
mutex_init(&memcg->thresholds_lock);
spin_lock_init(&memcg->move_lock);
res_counter_init(&memcg->kmem, &parent->kmem);
/*
- * We increment refcnt of the parent to ensure that we can
- * safely access it on res_counter_charge/uncharge.
- * This refcnt will be decremented when freeing this
- * mem_cgroup(see mem_cgroup_put).
+ * No need to take a reference to the parent because cgroup
+ * core guarantees its existence.
*/
- mem_cgroup_get(parent);
} else {
res_counter_init(&memcg->res, NULL);
res_counter_init(&memcg->memsw, NULL);
{
struct mem_cgroup *from = mc.from;
struct mem_cgroup *to = mc.to;
+ int i;
/* we must uncharge all the leftover precharges from mc.to */
if (mc.precharge) {
if (!mem_cgroup_is_root(mc.from))
res_counter_uncharge(&mc.from->memsw,
PAGE_SIZE * mc.moved_swap);
- __mem_cgroup_put(mc.from, mc.moved_swap);
+
+ for (i = 0; i < mc.moved_swap; i++)
+ css_put(&mc.from->css);
if (!mem_cgroup_is_root(mc.to)) {
/*
res_counter_uncharge(&mc.to->res,
PAGE_SIZE * mc.moved_swap);
}
- /* we've already done mem_cgroup_get(mc.to) */
+ /* we've already done css_get(mc.to) */
mc.moved_swap = 0;
}
memcg_oom_recover(from);