#endif
-/*
- * Statistics for memory cgroup.
- */
-enum mem_cgroup_stat_index {
- /*
- * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
- */
- MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
- MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */
- MEM_CGROUP_STAT_RSS_HUGE, /* # of pages charged as anon huge */
- MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */
- MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */
- MEM_CGROUP_STAT_NSTATS,
-};
-
static const char * const mem_cgroup_stat_names[] = {
"cache",
"rss",
"rss_huge",
"mapped_file",
+ "writeback",
"swap",
};
bool oom_lock;
atomic_t under_oom;
+ atomic_t oom_wakeups;
int swappiness;
/* OOM-Killer disable */
* Should we move charges of a task when a task is moved into this
* mem_cgroup ? And what type of charges should we move ?
*/
- unsigned long move_charge_at_immigrate;
+ unsigned long move_charge_at_immigrate;
/*
* set > 0 if pages under this cgroup are moving to other cgroup.
*/
*/
static DEFINE_MUTEX(memcg_create_mutex);
-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. */
preempt_enable();
}
-struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
-{
- return mem_cgroup_from_css(
- cgroup_subsys_state(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;
-
- /*
- * Root is not visited by cgroup iterators so it needs an
- * explicit visit.
- */
- if (!last_visited)
- return root;
+ struct cgroup_subsys_state *prev_css, *next_css;
- prev_cgroup = (last_visited == root) ? NULL
- : last_visited->css.cgroup;
+ prev_css = last_visited ? &last_visited->css : NULL;
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;
}
}
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;
check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
for_each_mem_cgroup_tree(iter, memcg) {
- struct cgroup *cgroup = iter->css.cgroup;
- struct cgroup_iter it;
+ struct css_task_iter it;
struct task_struct *task;
- cgroup_iter_start(cgroup, &it);
- while ((task = cgroup_iter_next(cgroup, &it))) {
+ css_task_iter_start(&iter->css, &it);
+ while ((task = css_task_iter_next(&it))) {
switch (oom_scan_process_thread(task, totalpages, NULL,
false)) {
case OOM_SCAN_SELECT:
case OOM_SCAN_CONTINUE:
continue;
case OOM_SCAN_ABORT:
- cgroup_iter_end(cgroup, &it);
+ css_task_iter_end(&it);
mem_cgroup_iter_break(memcg, iter);
if (chosen)
put_task_struct(chosen);
get_task_struct(chosen);
}
}
- cgroup_iter_end(cgroup, &it);
+ css_task_iter_end(&it);
}
if (!chosen)
return total;
}
+static DEFINE_SPINLOCK(memcg_oom_lock);
+
/*
* Check OOM-Killer is already running under our hierarchy.
* If someone is running, return false.
- * Has to be called with memcg_oom_lock
*/
-static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg)
+static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg)
{
struct mem_cgroup *iter, *failed = NULL;
+ spin_lock(&memcg_oom_lock);
+
for_each_mem_cgroup_tree(iter, memcg) {
if (iter->oom_lock) {
/*
iter->oom_lock = true;
}
- if (!failed)
- return true;
-
- /*
- * OK, we failed to lock the whole subtree so we have to clean up
- * what we set up to the failing subtree
- */
- for_each_mem_cgroup_tree(iter, memcg) {
- if (iter == failed) {
- mem_cgroup_iter_break(memcg, iter);
- break;
+ if (failed) {
+ /*
+ * OK, we failed to lock the whole subtree so we have
+ * to clean up what we set up to the failing subtree
+ */
+ for_each_mem_cgroup_tree(iter, memcg) {
+ if (iter == failed) {
+ mem_cgroup_iter_break(memcg, iter);
+ break;
+ }
+ iter->oom_lock = false;
}
- iter->oom_lock = false;
}
- return false;
+
+ spin_unlock(&memcg_oom_lock);
+
+ return !failed;
}
-/*
- * Has to be called with memcg_oom_lock
- */
-static int mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
+static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
{
struct mem_cgroup *iter;
+ spin_lock(&memcg_oom_lock);
for_each_mem_cgroup_tree(iter, memcg)
iter->oom_lock = false;
- return 0;
+ spin_unlock(&memcg_oom_lock);
}
static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg)
atomic_add_unless(&iter->under_oom, -1, 0);
}
-static DEFINE_SPINLOCK(memcg_oom_lock);
static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);
struct oom_wait_info {
static void memcg_wakeup_oom(struct mem_cgroup *memcg)
{
+ atomic_inc(&memcg->oom_wakeups);
/* for filtering, pass "memcg" as argument. */
__wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
}
}
/*
- * try to call OOM killer. returns false if we should exit memory-reclaim loop.
+ * try to call OOM killer
*/
-static bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask,
- int order)
+static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
{
- struct oom_wait_info owait;
- bool locked, need_to_kill;
+ bool locked;
+ int wakeups;
- owait.memcg = memcg;
- owait.wait.flags = 0;
- owait.wait.func = memcg_oom_wake_function;
- owait.wait.private = current;
- INIT_LIST_HEAD(&owait.wait.task_list);
- need_to_kill = true;
- mem_cgroup_mark_under_oom(memcg);
+ if (!current->memcg_oom.may_oom)
+ return;
+
+ current->memcg_oom.in_memcg_oom = 1;
- /* At first, try to OOM lock hierarchy under memcg.*/
- spin_lock(&memcg_oom_lock);
- locked = mem_cgroup_oom_lock(memcg);
/*
- * Even if signal_pending(), we can't quit charge() loop without
- * accounting. So, UNINTERRUPTIBLE is appropriate. But SIGKILL
- * under OOM is always welcomed, use TASK_KILLABLE here.
+ * As with any blocking lock, a contender needs to start
+ * listening for wakeups before attempting the trylock,
+ * otherwise it can miss the wakeup from the unlock and sleep
+ * indefinitely. This is just open-coded because our locking
+ * is so particular to memcg hierarchies.
*/
- prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
- if (!locked || memcg->oom_kill_disable)
- need_to_kill = false;
+ wakeups = atomic_read(&memcg->oom_wakeups);
+ mem_cgroup_mark_under_oom(memcg);
+
+ locked = mem_cgroup_oom_trylock(memcg);
+
if (locked)
mem_cgroup_oom_notify(memcg);
- spin_unlock(&memcg_oom_lock);
- if (need_to_kill) {
- finish_wait(&memcg_oom_waitq, &owait.wait);
+ if (locked && !memcg->oom_kill_disable) {
+ mem_cgroup_unmark_under_oom(memcg);
mem_cgroup_out_of_memory(memcg, mask, order);
+ mem_cgroup_oom_unlock(memcg);
+ /*
+ * There is no guarantee that an OOM-lock contender
+ * sees the wakeups triggered by the OOM kill
+ * uncharges. Wake any sleepers explicitely.
+ */
+ memcg_oom_recover(memcg);
} else {
- schedule();
- finish_wait(&memcg_oom_waitq, &owait.wait);
+ /*
+ * A system call can just return -ENOMEM, but if this
+ * is a page fault and somebody else is handling the
+ * OOM already, we need to sleep on the OOM waitqueue
+ * for this memcg until the situation is resolved.
+ * Which can take some time because it might be
+ * handled by a userspace task.
+ *
+ * However, this is the charge context, which means
+ * that we may sit on a large call stack and hold
+ * various filesystem locks, the mmap_sem etc. and we
+ * don't want the OOM handler to deadlock on them
+ * while we sit here and wait. Store the current OOM
+ * context in the task_struct, then return -ENOMEM.
+ * At the end of the page fault handler, with the
+ * stack unwound, pagefault_out_of_memory() will check
+ * back with us by calling
+ * mem_cgroup_oom_synchronize(), possibly putting the
+ * task to sleep.
+ */
+ current->memcg_oom.oom_locked = locked;
+ current->memcg_oom.wakeups = wakeups;
+ css_get(&memcg->css);
+ current->memcg_oom.wait_on_memcg = memcg;
}
- spin_lock(&memcg_oom_lock);
- if (locked)
- mem_cgroup_oom_unlock(memcg);
- memcg_wakeup_oom(memcg);
- spin_unlock(&memcg_oom_lock);
+}
- mem_cgroup_unmark_under_oom(memcg);
+/**
+ * mem_cgroup_oom_synchronize - complete memcg OOM handling
+ *
+ * This has to be called at the end of a page fault if the the memcg
+ * OOM handler was enabled and the fault is returning %VM_FAULT_OOM.
+ *
+ * Memcg supports userspace OOM handling, so failed allocations must
+ * sleep on a waitqueue until the userspace task resolves the
+ * situation. Sleeping directly in the charge context with all kinds
+ * of locks held is not a good idea, instead we remember an OOM state
+ * in the task and mem_cgroup_oom_synchronize() has to be called at
+ * the end of the page fault to put the task to sleep and clean up the
+ * OOM state.
+ *
+ * Returns %true if an ongoing memcg OOM situation was detected and
+ * finalized, %false otherwise.
+ */
+bool mem_cgroup_oom_synchronize(void)
+{
+ struct oom_wait_info owait;
+ struct mem_cgroup *memcg;
- if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
+ /* OOM is global, do not handle */
+ if (!current->memcg_oom.in_memcg_oom)
return false;
- /* Give chance to dying process */
- schedule_timeout_uninterruptible(1);
+
+ /*
+ * We invoked the OOM killer but there is a chance that a kill
+ * did not free up any charges. Everybody else might already
+ * be sleeping, so restart the fault and keep the rampage
+ * going until some charges are released.
+ */
+ memcg = current->memcg_oom.wait_on_memcg;
+ if (!memcg)
+ goto out;
+
+ if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
+ goto out_memcg;
+
+ owait.memcg = memcg;
+ owait.wait.flags = 0;
+ owait.wait.func = memcg_oom_wake_function;
+ owait.wait.private = current;
+ INIT_LIST_HEAD(&owait.wait.task_list);
+
+ prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
+ /* Only sleep if we didn't miss any wakeups since OOM */
+ if (atomic_read(&memcg->oom_wakeups) == current->memcg_oom.wakeups)
+ schedule();
+ finish_wait(&memcg_oom_waitq, &owait.wait);
+out_memcg:
+ mem_cgroup_unmark_under_oom(memcg);
+ if (current->memcg_oom.oom_locked) {
+ mem_cgroup_oom_unlock(memcg);
+ /*
+ * There is no guarantee that an OOM-lock contender
+ * sees the wakeups triggered by the OOM kill
+ * uncharges. Wake any sleepers explicitely.
+ */
+ memcg_oom_recover(memcg);
+ }
+ css_put(&memcg->css);
+ current->memcg_oom.wait_on_memcg = NULL;
+out:
+ current->memcg_oom.in_memcg_oom = 0;
return true;
}
}
void mem_cgroup_update_page_stat(struct page *page,
- enum mem_cgroup_page_stat_item idx, int val)
+ enum mem_cgroup_stat_index idx, int val)
{
struct mem_cgroup *memcg;
struct page_cgroup *pc = lookup_page_cgroup(page);
if (mem_cgroup_disabled())
return;
+ VM_BUG_ON(!rcu_read_lock_held());
memcg = pc->mem_cgroup;
if (unlikely(!memcg || !PageCgroupUsed(pc)))
return;
- switch (idx) {
- case MEMCG_NR_FILE_MAPPED:
- idx = MEM_CGROUP_STAT_FILE_MAPPED;
- break;
- default:
- BUG();
- }
-
this_cpu_add(memcg->stat->count[idx], val);
}
flush_work(&stock->work);
}
out:
- put_online_cpus();
+ put_online_cpus();
}
/*
CHARGE_RETRY, /* need to retry but retry is not bad */
CHARGE_NOMEM, /* we can't do more. return -ENOMEM */
CHARGE_WOULDBLOCK, /* GFP_WAIT wasn't set and no enough res. */
- CHARGE_OOM_DIE, /* the current is killed because of OOM */
};
static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
unsigned int nr_pages, unsigned int min_pages,
- bool oom_check)
+ bool invoke_oom)
{
unsigned long csize = nr_pages * PAGE_SIZE;
struct mem_cgroup *mem_over_limit;
if (mem_cgroup_wait_acct_move(mem_over_limit))
return CHARGE_RETRY;
- /* If we don't need to call oom-killer at el, return immediately */
- if (!oom_check)
- return CHARGE_NOMEM;
- /* check OOM */
- if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask, get_order(csize)))
- return CHARGE_OOM_DIE;
+ if (invoke_oom)
+ mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(csize));
- return CHARGE_RETRY;
+ return CHARGE_NOMEM;
}
/*
}
do {
- bool oom_check;
+ bool invoke_oom = oom && !nr_oom_retries;
/* If killed, bypass charge */
if (fatal_signal_pending(current)) {
goto bypass;
}
- oom_check = false;
- if (oom && !nr_oom_retries) {
- oom_check = true;
- nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
- }
-
- ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, nr_pages,
- oom_check);
+ ret = mem_cgroup_do_charge(memcg, gfp_mask, batch,
+ nr_pages, invoke_oom);
switch (ret) {
case CHARGE_OK:
break;
css_put(&memcg->css);
goto nomem;
case CHARGE_NOMEM: /* OOM routine works */
- if (!oom) {
+ if (!oom || invoke_oom) {
css_put(&memcg->css);
goto nomem;
}
- /* If oom, we never return -ENOMEM */
nr_oom_retries--;
break;
- case CHARGE_OOM_DIE: /* Killed by OOM Killer */
- css_put(&memcg->css);
- goto bypass;
}
} while (ret != CHARGE_OK);
* is accessed after testing USED bit. To make pc->mem_cgroup visible
* before USED bit, we need memory barrier here.
* See mem_cgroup_add_lru_list(), etc.
- */
+ */
smp_wmb();
SetPageCgroupUsed(pc);
}
#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))
ssize_t size = memcg_caches_array_size(num_groups);
size *= sizeof(void *);
- size += sizeof(struct memcg_cache_params);
+ size += offsetof(struct memcg_cache_params, memcg_caches);
s->memcg_params = kzalloc(size, GFP_KERNEL);
if (!s->memcg_params) {
int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
struct kmem_cache *root_cache)
{
- size_t size = sizeof(struct memcg_cache_params);
+ size_t size;
if (!memcg_kmem_enabled())
return 0;
- if (!memcg)
+ if (!memcg) {
+ size = offsetof(struct memcg_cache_params, memcg_caches);
size += memcg_limited_groups_array_size * sizeof(void *);
+ } else
+ size = sizeof(struct memcg_cache_params);
s->memcg_params = kzalloc(size, GFP_KERNEL);
if (!s->memcg_params)
* the page allocator. Therefore, the following sequence when backed by
* the SLUB allocator:
*
- * memcg_stop_kmem_account();
- * kmalloc(<large_number>)
- * memcg_resume_kmem_account();
+ * 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
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+static inline
+void mem_cgroup_move_account_page_stat(struct mem_cgroup *from,
+ struct mem_cgroup *to,
+ unsigned int nr_pages,
+ enum mem_cgroup_stat_index idx)
+{
+ /* Update stat data for mem_cgroup */
+ preempt_disable();
+ WARN_ON_ONCE(from->stat->count[idx] < nr_pages);
+ __this_cpu_add(from->stat->count[idx], -nr_pages);
+ __this_cpu_add(to->stat->count[idx], nr_pages);
+ preempt_enable();
+}
+
/**
* mem_cgroup_move_account - move account of the page
* @page: the page
move_lock_mem_cgroup(from, &flags);
- if (!anon && page_mapped(page)) {
- /* Update mapped_file data for mem_cgroup */
- preempt_disable();
- __this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
- __this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
- preempt_enable();
- }
+ if (!anon && page_mapped(page))
+ mem_cgroup_move_account_page_stat(from, to, nr_pages,
+ MEM_CGROUP_STAT_FILE_MAPPED);
+
+ if (PageWriteback(page))
+ mem_cgroup_move_account_page_stat(from, to, nr_pages,
+ MEM_CGROUP_STAT_WRITEBACK);
+
mem_cgroup_charge_statistics(from, page, anon, -nr_pages);
/* caller should have done css_get */
MEM_CGROUP_RECLAIM_SHRINK);
curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
/* Usage is reduced ? */
- if (curusage >= oldusage)
+ if (curusage >= oldusage)
retry_count--;
else
oldusage = curusage;
int enlarge = 0;
/* see mem_cgroup_resize_res_limit */
- retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
+ retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
while (retry_count) {
if (signal_pending(current)) {
*/
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);
- int ret;
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
if (mem_cgroup_is_root(memcg))
return -EINVAL;
- css_get(&memcg->css);
- ret = mem_cgroup_force_empty(memcg);
- css_put(&memcg->css);
-
- return ret;
+ return mem_cgroup_force_empty(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 (!memcg->kmem_account_flags && val != RES_COUNTER_MAX) {
+ if (cgroup_task_count(css->cgroup) || memcg_has_children(memcg)) {
ret = -EBUSY;
goto out;
}
ret = memcg_update_cache_sizes(memcg);
if (ret) {
- res_counter_set_limit(&memcg->kmem, RESOURCE_MAX);
+ res_counter_set_limit(&memcg->kmem, RES_COUNTER_MAX);
goto out;
}
static_key_slow_inc(&memcg_kmem_enabled_key);
* 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;
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+ struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css));
- if (val > 100)
+ if (val > 100 || !parent)
return -EINVAL;
- if (cgrp->parent == NULL)
- return -EINVAL;
-
- parent = mem_cgroup_from_cont(cgrp->parent);
-
mutex_lock(&memcg_create_mutex);
/* If under hierarchy, only empty-root can set this value */
const struct mem_cgroup_threshold *_a = a;
const struct mem_cgroup_threshold *_b = b;
- return _a->threshold - _b->threshold;
+ if (_a->threshold > _b->threshold)
+ return 1;
+
+ if (_a->threshold < _b->threshold)
+ return -1;
+
+ return 0;
}
static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg)
mem_cgroup_oom_notify_cb(iter);
}
-static int mem_cgroup_usage_register_event(struct cgroup *cgrp,
+static int mem_cgroup_usage_register_event(struct cgroup_subsys_state *css,
struct cftype *cft, struct eventfd_ctx *eventfd, const char *args)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct mem_cgroup_thresholds *thresholds;
struct mem_cgroup_threshold_ary *new;
enum res_type type = MEMFILE_TYPE(cft->private);
return ret;
}
-static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp,
+static void mem_cgroup_usage_unregister_event(struct cgroup_subsys_state *css,
struct cftype *cft, struct eventfd_ctx *eventfd)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct mem_cgroup_thresholds *thresholds;
struct mem_cgroup_threshold_ary *new;
enum res_type type = MEMFILE_TYPE(cft->private);
mutex_unlock(&memcg->thresholds_lock);
}
-static int mem_cgroup_oom_register_event(struct cgroup *cgrp,
+static int mem_cgroup_oom_register_event(struct cgroup_subsys_state *css,
struct cftype *cft, struct eventfd_ctx *eventfd, const char *args)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct mem_cgroup_eventfd_list *event;
enum res_type type = MEMFILE_TYPE(cft->private);
return 0;
}
-static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp,
+static void mem_cgroup_oom_unregister_event(struct cgroup_subsys_state *css,
struct cftype *cft, struct eventfd_ctx *eventfd)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct mem_cgroup_eventfd_list *ev, *tmp;
enum res_type type = MEMFILE_TYPE(cft->private);
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)) {
}
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);
}
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;
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);
vmpressure_cleanup(&memcg->vmpressure);
}
-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);
memcg_destroy_kmem(memcg);
__mem_cgroup_free(memcg);
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 = {
git.openpandora.org / pandora-kernel.git / blobdiff