struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
};
-struct mem_cgroup_lru_info {
- struct mem_cgroup_per_node *nodeinfo[0];
-};
-
/*
* Cgroups above their limits are maintained in a RB-Tree, independent of
* their hierarchy representation
/* 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;
atomic_t numainfo_updating;
#endif
- /*
- * Per cgroup active and inactive list, similar to the
- * per zone LRU lists.
- *
- * WARNING: This has to be the last element of the struct. Don't
- * add new fields after this point.
- */
- struct mem_cgroup_lru_info info;
+ struct mem_cgroup_per_node *nodeinfo[0];
+ /* WARNING: nodeinfo must be the last member here */
};
static size_t memcg_size(void)
static void memcg_kmem_mark_dead(struct mem_cgroup *memcg)
{
+ /*
+ * Our caller must use css_get() first, because memcg_uncharge_kmem()
+ * will call css_put() if it sees the memcg is dead.
+ */
+ smp_wmb();
if (test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags))
set_bit(KMEM_ACCOUNTED_DEAD, &memcg->kmem_account_flags);
}
*/
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)
{
- return container_of(s, struct mem_cgroup, css);
+ return s ? container_of(s, struct mem_cgroup, css) : NULL;
}
/* Some nice accessors for the vmpressure. */
*/
if (sk->sk_cgrp) {
BUG_ON(mem_cgroup_is_root(sk->sk_cgrp->memcg));
- mem_cgroup_get(sk->sk_cgrp->memcg);
+ css_get(&sk->sk_cgrp->memcg->css);
return;
}
rcu_read_lock();
memcg = mem_cgroup_from_task(current);
cg_proto = sk->sk_prot->proto_cgroup(memcg);
- if (!mem_cgroup_is_root(memcg) && memcg_proto_active(cg_proto)) {
- mem_cgroup_get(memcg);
+ if (!mem_cgroup_is_root(memcg) &&
+ memcg_proto_active(cg_proto) && css_tryget(&memcg->css)) {
sk->sk_cgrp = cg_proto;
}
rcu_read_unlock();
struct mem_cgroup *memcg;
WARN_ON(!sk->sk_cgrp->memcg);
memcg = sk->sk_cgrp->memcg;
- mem_cgroup_put(memcg);
+ css_put(&sk->sk_cgrp->memcg->css);
}
}
mem_cgroup_zoneinfo(struct mem_cgroup *memcg, int nid, int zid)
{
VM_BUG_ON((unsigned)nid >= nr_node_ids);
- return &memcg->info.nodeinfo[nid]->zoneinfo[zid];
+ return &memcg->nodeinfo[nid]->zoneinfo[zid];
}
struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg)
preempt_enable();
}
-struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
+static inline struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
{
- return mem_cgroup_from_css(
- cgroup_subsys_state(cont, mem_cgroup_subsys_id));
+ return mem_cgroup_from_css(cgroup_css(cont, mem_cgroup_subsys_id));
}
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
if (unlikely(!p))
return NULL;
- return mem_cgroup_from_css(task_subsys_state(p, mem_cgroup_subsys_id));
+ return mem_cgroup_from_css(task_css(p, mem_cgroup_subsys_id));
}
struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root,
struct mem_cgroup *last_visited)
{
- struct cgroup *prev_cgroup, *next_cgroup;
+ struct cgroup_subsys_state *prev_css, *next_css;
/*
* Root is not visited by cgroup iterators so it needs an
if (!last_visited)
return root;
- prev_cgroup = (last_visited == root) ? NULL
- : last_visited->css.cgroup;
+ prev_css = (last_visited == root) ? NULL : &last_visited->css;
skip_node:
- next_cgroup = cgroup_next_descendant_pre(
- prev_cgroup, root->css.cgroup);
+ next_css = css_next_descendant_pre(prev_css, &root->css);
/*
* Even if we found a group we have to make sure it is
* last_visited css is safe to use because it is
* protected by css_get and the tree walk is rcu safe.
*/
- if (next_cgroup) {
- struct mem_cgroup *mem = mem_cgroup_from_cont(
- next_cgroup);
+ if (next_css) {
+ struct mem_cgroup *mem = mem_cgroup_from_css(next_css);
+
if (css_tryget(&mem->css))
return mem;
else {
- prev_cgroup = next_cgroup;
+ prev_css = next_css;
goto skip_node;
}
}
return NULL;
}
+static void mem_cgroup_iter_invalidate(struct mem_cgroup *root)
+{
+ /*
+ * When a group in the hierarchy below root is destroyed, the
+ * hierarchy iterator can no longer be trusted since it might
+ * have pointed to the destroyed group. Invalidate it.
+ */
+ atomic_inc(&root->dead_count);
+}
+
+static struct mem_cgroup *
+mem_cgroup_iter_load(struct mem_cgroup_reclaim_iter *iter,
+ struct mem_cgroup *root,
+ int *sequence)
+{
+ struct mem_cgroup *position = NULL;
+ /*
+ * A cgroup destruction happens in two stages: offlining and
+ * release. They are separated by a RCU grace period.
+ *
+ * If the iterator is valid, we may still race with an
+ * offlining. The RCU lock ensures the object won't be
+ * released, tryget will fail if we lost the race.
+ */
+ *sequence = atomic_read(&root->dead_count);
+ if (iter->last_dead_count == *sequence) {
+ smp_rmb();
+ position = iter->last_visited;
+ if (position && !css_tryget(&position->css))
+ position = NULL;
+ }
+ return position;
+}
+
+static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter,
+ struct mem_cgroup *last_visited,
+ struct mem_cgroup *new_position,
+ int sequence)
+{
+ if (last_visited)
+ css_put(&last_visited->css);
+ /*
+ * We store the sequence count from the time @last_visited was
+ * loaded successfully instead of rereading it here so that we
+ * don't lose destruction events in between. We could have
+ * raced with the destruction of @new_position after all.
+ */
+ iter->last_visited = new_position;
+ smp_wmb();
+ iter->last_dead_count = sequence;
+}
+
/**
* mem_cgroup_iter - iterate over memory cgroup hierarchy
* @root: hierarchy root
{
struct mem_cgroup *memcg = NULL;
struct mem_cgroup *last_visited = NULL;
- unsigned long uninitialized_var(dead_count);
if (mem_cgroup_disabled())
return NULL;
rcu_read_lock();
while (!memcg) {
struct mem_cgroup_reclaim_iter *uninitialized_var(iter);
+ int uninitialized_var(seq);
if (reclaim) {
int nid = zone_to_nid(reclaim->zone);
goto out_unlock;
}
- /*
- * If the dead_count mismatches, a destruction
- * has happened or is happening concurrently.
- * If the dead_count matches, a destruction
- * might still happen concurrently, but since
- * we checked under RCU, that destruction
- * won't free the object until we release the
- * RCU reader lock. Thus, the dead_count
- * check verifies the pointer is still valid,
- * css_tryget() verifies the cgroup pointed to
- * is alive.
- */
- dead_count = atomic_read(&root->dead_count);
- if (dead_count == iter->last_dead_count) {
- smp_rmb();
- last_visited = iter->last_visited;
- if (last_visited &&
- !css_tryget(&last_visited->css))
- last_visited = NULL;
- }
+ last_visited = mem_cgroup_iter_load(iter, root, &seq);
}
memcg = __mem_cgroup_iter_next(root, last_visited);
if (reclaim) {
- if (last_visited)
- css_put(&last_visited->css);
-
- iter->last_visited = memcg;
- smp_wmb();
- iter->last_dead_count = dead_count;
+ mem_cgroup_iter_update(iter, last_visited, memcg, seq);
if (!memcg)
iter->generation++;
int mem_cgroup_swappiness(struct mem_cgroup *memcg)
{
- struct cgroup *cgrp = memcg->css.cgroup;
-
/* root ? */
- if (cgrp->parent == NULL)
+ if (!css_parent(&memcg->css))
return vm_swappiness;
return memcg->swappiness;
}
#ifdef CONFIG_SLABINFO
-static int mem_cgroup_slabinfo_read(struct cgroup *cont, struct cftype *cft,
- struct seq_file *m)
+static int mem_cgroup_slabinfo_read(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct seq_file *m)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct memcg_cache_params *params;
if (!memcg_can_account_kmem(memcg))
if (res_counter_uncharge(&memcg->kmem, size))
return;
+ /*
+ * Releases a reference taken in kmem_cgroup_css_offline in case
+ * this last uncharge is racing with the offlining code or it is
+ * outliving the memcg existence.
+ *
+ * The memory barrier imposed by test&clear is paired with the
+ * explicit one in memcg_kmem_mark_dead().
+ */
if (memcg_kmem_test_and_clear_dead(memcg))
- mem_cgroup_put(memcg);
+ css_put(&memcg->css);
}
void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep)
list_del(&s->memcg_params->list);
mutex_unlock(&memcg->slab_caches_mutex);
- mem_cgroup_put(memcg);
+ css_put(&memcg->css);
out:
kfree(s->memcg_params);
}
mutex_lock(&memcg_cache_mutex);
new_cachep = cachep->memcg_params->memcg_caches[idx];
- if (new_cachep)
+ if (new_cachep) {
+ css_put(&memcg->css);
goto out;
+ }
new_cachep = kmem_cache_dup(memcg, cachep);
if (new_cachep == NULL) {
new_cachep = cachep;
+ css_put(&memcg->css);
goto out;
}
- mem_cgroup_get(memcg);
atomic_set(&new_cachep->memcg_params->nr_pages , 0);
cachep->memcg_params->memcg_caches[idx] = new_cachep;
cw = container_of(w, struct create_work, work);
memcg_create_kmem_cache(cw->memcg, cw->cachep);
- /* Drop the reference gotten when we enqueued. */
- css_put(&cw->memcg->css);
kfree(cw);
}
int ret;
*_memcg = NULL;
+
+ /*
+ * Disabling accounting is only relevant for some specific memcg
+ * internal allocations. Therefore we would initially not have such
+ * check here, since direct calls to the page allocator that are marked
+ * with GFP_KMEMCG only happen outside memcg core. We are mostly
+ * concerned with cache allocations, and by having this test at
+ * memcg_kmem_get_cache, we are already able to relay the allocation to
+ * the root cache and bypass the memcg cache altogether.
+ *
+ * There is one exception, though: the SLUB allocator does not create
+ * large order caches, but rather service large kmallocs directly from
+ * the page allocator. Therefore, the following sequence when backed by
+ * the SLUB allocator:
+ *
+ * memcg_stop_kmem_account();
+ * kmalloc(<large_number>)
+ * memcg_resume_kmem_account();
+ *
+ * would effectively ignore the fact that we should skip accounting,
+ * since it will drive us directly to this function without passing
+ * through the cache selector memcg_kmem_get_cache. Such large
+ * allocations are extremely rare but can happen, for instance, for the
+ * cache arrays. We bring this test here.
+ */
+ if (!current->mm || current->memcg_kmem_skip_account)
+ return true;
+
memcg = try_get_mem_cgroup_from_mm(current->mm);
/*
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;
*/
static inline bool __memcg_has_children(struct mem_cgroup *memcg)
{
- struct cgroup *pos;
+ struct cgroup_subsys_state *pos;
/* bounce at first found */
- cgroup_for_each_child(pos, memcg->css.cgroup)
+ css_for_each_child(pos, &memcg->css)
return true;
return false;
}
return 0;
}
-static int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event)
+static int mem_cgroup_force_empty_write(struct cgroup_subsys_state *css,
+ unsigned int event)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
int ret;
if (mem_cgroup_is_root(memcg))
}
-static u64 mem_cgroup_hierarchy_read(struct cgroup *cont, struct cftype *cft)
+static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css,
+ struct cftype *cft)
{
- return mem_cgroup_from_cont(cont)->use_hierarchy;
+ return mem_cgroup_from_css(css)->use_hierarchy;
}
-static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
- u64 val)
+static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css,
+ struct cftype *cft, u64 val)
{
int retval = 0;
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
- struct cgroup *parent = cont->parent;
- struct mem_cgroup *parent_memcg = NULL;
-
- if (parent)
- parent_memcg = mem_cgroup_from_cont(parent);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+ struct mem_cgroup *parent_memcg = mem_cgroup_from_css(css_parent(&memcg->css));
mutex_lock(&memcg_create_mutex);
return val << PAGE_SHIFT;
}
-static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft,
- struct file *file, char __user *buf,
- size_t nbytes, loff_t *ppos)
+static ssize_t mem_cgroup_read(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct file *file,
+ char __user *buf, size_t nbytes, loff_t *ppos)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
char str[64];
u64 val;
int name, len;
return simple_read_from_buffer(buf, nbytes, ppos, str, len);
}
-static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
+static int memcg_update_kmem_limit(struct cgroup_subsys_state *css, u64 val)
{
int ret = -EINVAL;
#ifdef CONFIG_MEMCG_KMEM
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
/*
* For simplicity, we won't allow this to be disabled. It also can't
* be changed if the cgroup has children already, or if tasks had
mutex_lock(&memcg_create_mutex);
mutex_lock(&set_limit_mutex);
if (!memcg->kmem_account_flags && val != RESOURCE_MAX) {
- if (cgroup_task_count(cont) || memcg_has_children(memcg)) {
+ if (cgroup_task_count(css->cgroup) || memcg_has_children(memcg)) {
ret = -EBUSY;
goto out;
}
* starts accounting before all call sites are patched
*/
memcg_kmem_set_active(memcg);
-
- /*
- * kmem charges can outlive the cgroup. In the case of slab
- * pages, for instance, a page contain objects from various
- * processes, so it is unfeasible to migrate them away. We
- * need to reference count the memcg because of that.
- */
- mem_cgroup_get(memcg);
} else
ret = res_counter_set_limit(&memcg->kmem, val);
out:
goto out;
/*
- * destroy(), called if we fail, will issue static_key_slow_inc() and
- * mem_cgroup_put() if kmem is enabled. We have to either call them
- * unconditionally, or clear the KMEM_ACTIVE flag. I personally find
- * this more consistent, since it always leads to the same destroy path
+ * __mem_cgroup_free() will issue static_key_slow_dec() because this
+ * memcg is active already. If the later initialization fails then the
+ * cgroup core triggers the cleanup so we do not have to do it here.
*/
- mem_cgroup_get(memcg);
static_key_slow_inc(&memcg_kmem_enabled_key);
mutex_lock(&set_limit_mutex);
+ memcg_stop_kmem_account();
ret = memcg_update_cache_sizes(memcg);
+ memcg_resume_kmem_account();
mutex_unlock(&set_limit_mutex);
out:
return ret;
* The user of this function is...
* RES_LIMIT.
*/
-static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
+static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
const char *buffer)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
enum res_type type;
int name;
unsigned long long val;
else if (type == _MEMSWAP)
ret = mem_cgroup_resize_memsw_limit(memcg, val);
else if (type == _KMEM)
- ret = memcg_update_kmem_limit(cont, val);
+ ret = memcg_update_kmem_limit(css, val);
else
return -EINVAL;
break;
static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg,
unsigned long long *mem_limit, unsigned long long *memsw_limit)
{
- struct cgroup *cgroup;
unsigned long long min_limit, min_memsw_limit, tmp;
min_limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
min_memsw_limit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
- cgroup = memcg->css.cgroup;
if (!memcg->use_hierarchy)
goto out;
- while (cgroup->parent) {
- cgroup = cgroup->parent;
- memcg = mem_cgroup_from_cont(cgroup);
+ while (css_parent(&memcg->css)) {
+ memcg = mem_cgroup_from_css(css_parent(&memcg->css));
if (!memcg->use_hierarchy)
break;
tmp = res_counter_read_u64(&memcg->res, RES_LIMIT);
*memsw_limit = min_memsw_limit;
}
-static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
+static int mem_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
int name;
enum res_type type;
return 0;
}
-static u64 mem_cgroup_move_charge_read(struct cgroup *cgrp,
+static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
- return mem_cgroup_from_cont(cgrp)->move_charge_at_immigrate;
+ return mem_cgroup_from_css(css)->move_charge_at_immigrate;
}
#ifdef CONFIG_MMU
-static int mem_cgroup_move_charge_write(struct cgroup *cgrp,
+static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css,
struct cftype *cft, u64 val)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
if (val >= (1 << NR_MOVE_TYPE))
return -EINVAL;
return 0;
}
#else
-static int mem_cgroup_move_charge_write(struct cgroup *cgrp,
+static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css,
struct cftype *cft, u64 val)
{
return -ENOSYS;
#endif
#ifdef CONFIG_NUMA
-static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
- struct seq_file *m)
+static int memcg_numa_stat_show(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct seq_file *m)
{
int nid;
unsigned long total_nr, file_nr, anon_nr, unevictable_nr;
unsigned long node_nr;
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
total_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL);
seq_printf(m, "total=%lu", total_nr);
BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS);
}
-static int memcg_stat_show(struct cgroup *cont, struct cftype *cft,
+static int memcg_stat_show(struct cgroup_subsys_state *css, struct cftype *cft,
struct seq_file *m)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct mem_cgroup *mi;
unsigned int i;
return 0;
}
-static u64 mem_cgroup_swappiness_read(struct cgroup *cgrp, struct cftype *cft)
+static u64 mem_cgroup_swappiness_read(struct cgroup_subsys_state *css,
+ struct cftype *cft)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
return mem_cgroup_swappiness(memcg);
}
-static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft,
- u64 val)
+static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css,
+ struct cftype *cft, u64 val)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
- struct mem_cgroup *parent;
-
- if (val > 100)
- return -EINVAL;
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+ struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css));
- if (cgrp->parent == NULL)
+ if (val > 100 || !parent)
return -EINVAL;
- parent = mem_cgroup_from_cont(cgrp->parent);
-
mutex_lock(&memcg_create_mutex);
/* If under hierarchy, only empty-root can set this value */
spin_unlock(&memcg_oom_lock);
}
-static int mem_cgroup_oom_control_read(struct cgroup *cgrp,
+static int mem_cgroup_oom_control_read(struct cgroup_subsys_state *css,
struct cftype *cft, struct cgroup_map_cb *cb)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
cb->fill(cb, "oom_kill_disable", memcg->oom_kill_disable);
return 0;
}
-static int mem_cgroup_oom_control_write(struct cgroup *cgrp,
+static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css,
struct cftype *cft, u64 val)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
- struct mem_cgroup *parent;
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+ struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css));
/* cannot set to root cgroup and only 0 and 1 are allowed */
- if (!cgrp->parent || !((val == 0) || (val == 1)))
+ if (!parent || !((val == 0) || (val == 1)))
return -EINVAL;
- parent = mem_cgroup_from_cont(cgrp->parent);
-
mutex_lock(&memcg_create_mutex);
/* oom-kill-disable is a flag for subhierarchy. */
if ((parent->use_hierarchy) || memcg_has_children(memcg)) {
return mem_cgroup_sockets_init(memcg, ss);
}
-static void kmem_cgroup_destroy(struct mem_cgroup *memcg)
+static void memcg_destroy_kmem(struct mem_cgroup *memcg)
{
mem_cgroup_sockets_destroy(memcg);
+}
+
+static void kmem_cgroup_css_offline(struct mem_cgroup *memcg)
+{
+ if (!memcg_kmem_is_active(memcg))
+ return;
+
+ /*
+ * kmem charges can outlive the cgroup. In the case of slab
+ * pages, for instance, a page contain objects from various
+ * processes. As we prevent from taking a reference for every
+ * such allocation we have to be careful when doing uncharge
+ * (see memcg_uncharge_kmem) and here during offlining.
+ *
+ * The idea is that that only the _last_ uncharge which sees
+ * the dead memcg will drop the last reference. An additional
+ * reference is taken here before the group is marked dead
+ * which is then paired with css_put during uncharge resp. here.
+ *
+ * Although this might sound strange as this path is called from
+ * css_offline() when the referencemight have dropped down to 0
+ * and shouldn't be incremented anymore (css_tryget would fail)
+ * we do not have other options because of the kmem allocations
+ * lifetime.
+ */
+ css_get(&memcg->css);
memcg_kmem_mark_dead(memcg);
if (res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0)
return;
- /*
- * Charges already down to 0, undo mem_cgroup_get() done in the charge
- * path here, being careful not to race with memcg_uncharge_kmem: it is
- * possible that the charges went down to 0 between mark_dead and the
- * res_counter read, so in that case, we don't need the put
- */
if (memcg_kmem_test_and_clear_dead(memcg))
- mem_cgroup_put(memcg);
+ css_put(&memcg->css);
}
#else
static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
return 0;
}
-static void kmem_cgroup_destroy(struct mem_cgroup *memcg)
+static void memcg_destroy_kmem(struct mem_cgroup *memcg)
+{
+}
+
+static void kmem_cgroup_css_offline(struct mem_cgroup *memcg)
{
}
#endif
mz->on_tree = false;
mz->memcg = memcg;
}
- memcg->info.nodeinfo[node] = pn;
+ memcg->nodeinfo[node] = pn;
return 0;
}
static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
{
- kfree(memcg->info.nodeinfo[node]);
+ kfree(memcg->nodeinfo[node]);
}
static struct mem_cgroup *mem_cgroup_alloc(void)
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.
*/
}
static struct cgroup_subsys_state * __ref
-mem_cgroup_css_alloc(struct cgroup *cont)
+mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct mem_cgroup *memcg;
long error = -ENOMEM;
goto free_out;
/* root ? */
- if (cont->parent == NULL) {
+ if (parent_css == NULL) {
root_mem_cgroup = memcg;
res_counter_init(&memcg->res, NULL);
res_counter_init(&memcg->memsw, NULL);
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);
}
static int
-mem_cgroup_css_online(struct cgroup *cont)
+mem_cgroup_css_online(struct cgroup_subsys_state *css)
{
- struct mem_cgroup *memcg, *parent;
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+ struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css));
int error = 0;
- if (!cont->parent)
+ if (!parent)
return 0;
mutex_lock(&memcg_create_mutex);
- memcg = mem_cgroup_from_cont(cont);
- parent = mem_cgroup_from_cont(cont->parent);
memcg->use_hierarchy = parent->use_hierarchy;
memcg->oom_kill_disable = parent->oom_kill_disable;
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);
error = memcg_init_kmem(memcg, &mem_cgroup_subsys);
mutex_unlock(&memcg_create_mutex);
- if (error) {
- /*
- * We call put now because our (and parent's) refcnts
- * are already in place. mem_cgroup_put() will internally
- * call __mem_cgroup_free, so return directly
- */
- mem_cgroup_put(memcg);
- if (parent->use_hierarchy)
- mem_cgroup_put(parent);
- }
return error;
}
struct mem_cgroup *parent = memcg;
while ((parent = parent_mem_cgroup(parent)))
- atomic_inc(&parent->dead_count);
+ mem_cgroup_iter_invalidate(parent);
/*
* if the root memcg is not hierarchical we have to check it
* explicitely.
*/
if (!root_mem_cgroup->use_hierarchy)
- atomic_inc(&root_mem_cgroup->dead_count);
+ mem_cgroup_iter_invalidate(root_mem_cgroup);
}
-static void mem_cgroup_css_offline(struct cgroup *cont)
+static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+
+ kmem_cgroup_css_offline(memcg);
mem_cgroup_invalidate_reclaim_iterators(memcg);
mem_cgroup_reparent_charges(memcg);
mem_cgroup_destroy_all_caches(memcg);
}
-static void mem_cgroup_css_free(struct cgroup *cont)
+static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
- kmem_cgroup_destroy(memcg);
-
- mem_cgroup_put(memcg);
+ memcg_destroy_kmem(memcg);
+ __mem_cgroup_free(memcg);
}
#ifdef CONFIG_MMU
{
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);
mem_cgroup_end_move(from);
}
-static int mem_cgroup_can_attach(struct cgroup *cgroup,
+static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
struct task_struct *p = cgroup_taskset_first(tset);
int ret = 0;
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
unsigned long move_charge_at_immigrate;
/*
return ret;
}
-static void mem_cgroup_cancel_attach(struct cgroup *cgroup,
+static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
mem_cgroup_clear_mc();
up_read(&mm->mmap_sem);
}
-static void mem_cgroup_move_task(struct cgroup *cont,
+static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
struct task_struct *p = cgroup_taskset_first(tset);
mem_cgroup_clear_mc();
}
#else /* !CONFIG_MMU */
-static int mem_cgroup_can_attach(struct cgroup *cgroup,
+static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
return 0;
}
-static void mem_cgroup_cancel_attach(struct cgroup *cgroup,
+static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
}
-static void mem_cgroup_move_task(struct cgroup *cont,
+static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
}
* Cgroup retains root cgroups across [un]mount cycles making it necessary
* to verify sane_behavior flag on each mount attempt.
*/
-static void mem_cgroup_bind(struct cgroup *root)
+static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
{
/*
* use_hierarchy is forced with sane_behavior. cgroup core
* guarantees that @root doesn't have any children, so turning it
* on for the root memcg is enough.
*/
- if (cgroup_sane_behavior(root))
- mem_cgroup_from_cont(root)->use_hierarchy = true;
+ if (cgroup_sane_behavior(root_css->cgroup))
+ mem_cgroup_from_css(root_css)->use_hierarchy = true;
}
struct cgroup_subsys mem_cgroup_subsys = {