*/
bool use_hierarchy;
unsigned long last_oom_jiffies;
- int obsolete;
atomic_t refcnt;
unsigned int swappiness;
struct mem_cgroup, css);
}
+static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
+{
+ struct mem_cgroup *mem = NULL;
+ /*
+ * Because we have no locks, mm->owner's may be being moved to other
+ * cgroup. We use css_tryget() here even if this looks
+ * pessimistic (rather than adding locks here).
+ */
+ rcu_read_lock();
+ do {
+ mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+ if (unlikely(!mem))
+ break;
+ } while (!css_tryget(&mem->css));
+ rcu_read_unlock();
+ return mem;
+}
+
+static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem)
+{
+ if (!mem)
+ return true;
+ return css_is_removed(&mem->css);
+}
+
/*
* Following LRU functions are allowed to be used without PCG_LOCK.
* Operations are called by routine of global LRU independently from memcg.
{
struct cgroup *cgroup;
struct mem_cgroup *ret;
- bool obsolete = (root_mem->last_scanned_child &&
- root_mem->last_scanned_child->obsolete);
+ bool obsolete;
+
+ obsolete = mem_cgroup_is_obsolete(root_mem->last_scanned_child);
/*
* Scan all children under the mem_cgroup mem
if (!root_mem->last_scanned_child || obsolete) {
- if (obsolete)
+ if (obsolete && root_mem->last_scanned_child)
mem_cgroup_put(root_mem->last_scanned_child);
cgroup = list_first_entry(&root_mem->css.cgroup->children,
next_mem = mem_cgroup_get_first_node(root_mem);
while (next_mem != root_mem) {
- if (next_mem->obsolete) {
+ if (mem_cgroup_is_obsolete(next_mem)) {
mem_cgroup_put(next_mem);
cgroup_lock();
next_mem = mem_cgroup_get_first_node(root_mem);
* thread group leader migrates. It's possible that mm is not
* set, if so charge the init_mm (happens for pagecache usage).
*/
- if (likely(!*memcg)) {
- rcu_read_lock();
- mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
- if (unlikely(!mem)) {
- rcu_read_unlock();
- return 0;
- }
- /*
- * For every charge from the cgroup, increment reference count
- */
- css_get(&mem->css);
+ mem = *memcg;
+ if (likely(!mem)) {
+ mem = try_get_mem_cgroup_from_mm(mm);
*memcg = mem;
- rcu_read_unlock();
} else {
- mem = *memcg;
css_get(&mem->css);
}
+ if (unlikely(!mem))
+ return 0;
+
+ VM_BUG_ON(mem_cgroup_is_obsolete(mem));
while (1) {
int ret;
MEM_CGROUP_CHARGE_TYPE_SHMEM, NULL);
}
+/*
+ * 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 aquired. This refcnt will be cumsumed by
+ * "commit()" or removed by "cancel()"
+ */
int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
struct page *page,
gfp_t mask, struct mem_cgroup **ptr)
{
struct mem_cgroup *mem;
swp_entry_t ent;
+ int ret;
if (mem_cgroup_disabled())
return 0;
ent.val = page_private(page);
mem = lookup_swap_cgroup(ent);
- if (!mem || mem->obsolete)
+ if (!mem)
+ goto charge_cur_mm;
+ if (!css_tryget(&mem->css))
goto charge_cur_mm;
*ptr = mem;
- return __mem_cgroup_try_charge(NULL, mask, ptr, true);
+ ret = __mem_cgroup_try_charge(NULL, mask, ptr, true);
+ /* drop extra refcnt from tryget */
+ css_put(&mem->css);
+ return ret;
charge_cur_mm:
if (unlikely(!mm))
mm = &init_mm;
ent.val = page_private(page);
if (do_swap_account) {
mem = lookup_swap_cgroup(ent);
- if (mem && mem->obsolete)
- mem = NULL;
- if (mem)
- mm = NULL;
+ if (mem) {
+ if (css_tryget(&mem->css))
+ mm = NULL; /* charge to recorded */
+ else
+ mem = NULL; /* charge to current */
+ }
}
ret = mem_cgroup_charge_common(page, mm, mask,
MEM_CGROUP_CHARGE_TYPE_SHMEM, mem);
+ /* drop extra refcnt from tryget */
+ if (mem)
+ css_put(&mem->css);
if (!ret && do_swap_account) {
/* avoid double counting */
struct mem_cgroup *memcg;
memcg = swap_cgroup_record(ent, NULL);
if (memcg) {
- /* If memcg is obsolete, memcg can be != ptr */
res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
mem_cgroup_put(memcg);
}
if (!mm)
return 0;
- rcu_read_lock();
- mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
- if (unlikely(!mem)) {
- rcu_read_unlock();
+ mem = try_get_mem_cgroup_from_mm(mm);
+ if (unlikely(!mem))
return 0;
- }
- css_get(&mem->css);
- rcu_read_unlock();
do {
progress = mem_cgroup_hierarchical_reclaim(mem, gfp_mask, true);
* the number of reference from swap_cgroup and free mem_cgroup when
* it goes down to 0.
*
- * When mem_cgroup is destroyed, mem->obsolete will be set to 0 and
- * entry which points to this memcg will be ignore at swapin.
- *
* Removal of cgroup itself succeeds regardless of refs from swap.
*/
struct cgroup *cont)
{
struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
- mem->obsolete = 1;
mem_cgroup_force_empty(mem, false);
}